Connect with us

Noticias

Remember the Legal Research ‘AI Smackdown’? I Decided To Bring OpenAI’s Deep Research to the Fight

Published

on

Recently, I wrote here about the AI Smackdown presented at a Feb. 8 meeting of the Southern California Association of Law Libraries, where a panel of three law librarians reported on their comparison of the AI answers delivered by three leading platforms – Lexis+AI, Westlaw Precision AI, and vLex’s Vincent AI.

Having been playing around of late with Deep Research, the AI agent from OpenAI that is capable of completing multi-step research tasks and synthesizing large amounts of online information, I wondered how much of a contender it could be against those legal research prizefighters. 

[My other Deep Research posts: What Is OpenAI’s Powerful New Deep Research Tool Capable Of? I Use It to Analyze the Legality of President Trump’s Pause of Federal Grants; Today’s Experiment with OpenAI’s Deep Research: Picking the Best Cloud-Based Law Practice Management Software for a Small Law Firm; A Compendium of Legal Ethics Opinions on Gen AI (As Compiled by – You Guessed It – Gen AI).]

To test it, I decided to start with just one of the three questions the law librarians used in their smackdown. Of the three questions they threw into the ring, one turned out to be particularly tricky and elicited much-different answers from each of the commercial legal research platforms. That question was:

“What is the standard for appealing class certification? (California)”

What made it tricky was something called the “death knell” doctrine, which requires that denials of class actions in California be appealed immediately.

In the law librarians’ smackdown, all three legal research platforms gave the right answer as to the standard for appealing. However, their answers varied widely on the death knell issue and the need to file an immediate appeal — which, as Cindy Guyer, senior knowledge and research analyst at O’Melveny & Myers, the librarian who conducted the test of that question, said, is “kind of important.” 

Lexis+ AI made no mention of the death knell issue. Westlaw Precision AI did include a warning about the need for immediate appeal, but presented it in a way that was potentially confusing and might not have alerted a researcher. Only Vincent AI gave what Guyer described as a “great answer,” which included a special section that highlighted the death knell issue.

So how did OpenAI’s Deep Research do? Its full answer is reproduced below, but — spoiler alert — it picked right up on the death knell issue.

As a matter of fact, it zeroed in on this issue even before it finished its research. One of the funny things Deep Research does is offer a running commentary on its progress as it researches an issue. As you can see from the excerpt to the right, it quickly began “digging into the ‘death knell’ doctrine,” as it says.

And in the memo it produced, it gets right into the doctrine, devoting a substantial section to it right at the beginning of the memo.

Worth remembering is that Deep Research does not have access to paywalled legal research services, such as the three services in the smackdown. It conducts its research using only public-facing sources. (Ironically, perhaps, one of those sources is Casetext, the company acquired by Thomson Reuters, whose case law is still publicly accessible — for now anyway.)

One can only wonder how Deep Research would do if it could access a more robust legal research database. Would Deep Research be the death knell for commercial legal research?

Meanwhile, here is its memo, in its entirely. All of the citations were added by Deep Research.


Class certification orders in California state courts present unique challenges for appeal. Generally, California follows the “one final judgment” rule, meaning only final judgments are appealable as of right (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). An order granting or denying class certification is interlocutory (it does not end the case), so it is not usually appealable under the final judgment rule (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). However, California courts have developed special doctrines and procedures to allow review of class certification decisions in appropriate circumstances. This analysis outlines the California framework for appealing class certification orders, including the grounds for appeal, availability of interlocutory review, appellate courts’ standards, and the procedural steps (deadlines and filings) required to initiate an appeal.

Appealability of Class Certification Orders in California

Final Judgment Rule: Under Code of Civil Procedure § 904.1, parties generally may only appeal a final judgment or order that disposes of all causes of action (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). A class certification order typically does not resolve the entire case; if class status is denied, the named plaintiff’s individual claims remain, and if class status is granted, the case proceeds on the merits. Thus, a class certification ruling is usually an interlocutory order not listed as directly appealable under § 904.1. California courts focus on an order’s legal effect rather than its form to determine appealability (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). In the class context, an interlocutory order may be treated as appealable if it effectively ends the litigation for a large portion of the parties (such as absent class members), even if the named plaintiff’s claims continue (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group).

The “Death Knell” Doctrine: California’s “death knell” doctrine is the key exception that permits an immediate appeal from certain class certification orders. If a trial court denies class certification in its entirety (rejecting all class claims) and leaves only the named plaintiff’s individual claims, that order is treated as a de facto final judgment on the class issues (Litigating on the Fault Line: Class Action Law in California — Impact Fund) (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). In this scenario, the order “effectively terminates the entire action as to the class” – in legal effect it is “tantamount to a dismissal of the action as to all members of the class other than the plaintiff” (Litigating on the Fault Line: Class Action Law in California — Impact Fund) (quoting the California Supreme Court’s description in Daar v. Yellow Cab Co.). The rationale is that without immediate review, the class claims would likely never be revived: the named plaintiff may lack a financial incentive to pursue a costly individual case to final judgment just to enable an appeal on behalf of the class (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court) (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court). Thus, as a matter of state policy, such “death knell” orders are made appealable even though they are interlocutory (Litigating on the Fault Line: Class Action Law in California — Impact Fund) (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group).

Under the death knell doctrine, an order is immediately appealable if it (1) amounts to a de facto final judgment for the absent class members, and (2) the remaining individual claims are sufficiently small or impractical that there is a risk no final judgment on those claims will ever be reached (i.e. the plaintiff might abandon the case) (Miranda v. Anderson Enterprises, Inc., 241 Cal.App.4th 196 | Casetext Search + Citator). In other words, the doctrine applies when “the persistence of viable but perhaps de minimis individual plaintiff claims creates a risk no formal final judgment will ever be entered.” (Miranda v. Anderson Enterprises, Inc., 241 Cal.App.4th 196 | Casetext Search + Citator) (quoting In re Baycol Cases I & II, 51 Cal.4th 751, 759 (2011)). California courts have emphasized that the death knell exception is limited to orders denying class certification in their entirety (Litigating on the Fault Line: Class Action Law in California — Impact Fund). Partial class certification (for example, certifying one subclass and denying another) does not trigger an immediate right to appeal because some class aspect remains alive in the case (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court). Likewise, if a representative claim remains that gives the plaintiff incentive to continue (such as a pending PAGA claim for civil penalties on behalf of the state), the death knell doctrine usually will not apply (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court). In those situations, the plaintiff can still obtain review of the class certification decision at a later final judgment, so an immediate appeal is deemed unnecessary (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court). By contrast, if all class and representative claims are dismissed or denied (leaving only individual issues, or sending the plaintiff to individual arbitration), then the death knell doctrine allows an immediate appeal of that order (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group) (Miranda v. Anderson Enterprises, Inc., 241 Cal.App.4th 196 | Casetext Search + Citator).

Appeal as of Right in Death Knell Cases: When the death knell doctrine applies, the class certification denial is treated as an appealable order, giving the plaintiff (or would-be class representative) a right to appeal immediately to the Court of Appeal (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group). Importantly, this appeal must be taken promptly. The appellate courts have held that if the aggrieved party does not appeal the class certification denial when it falls under the death knell doctrine, the right to appellate review is forfeited – the order becomes final and cannot be challenged later (Litigating on the Fault Line: Class Action Law in California — Impact Fund). In practice, this means a notice of appeal must be filed within the normal deadline after notice of entry of the class-certification denial (discussed below), or the opportunity for immediate review is lost. (Once a death-knell order becomes final by failure to appeal, the plaintiff generally cannot later resurrect the class claims or appeal the issue after an eventual individual judgment (Stephen v. Enterprise Rent-A-Car, 235 Cal.App.3d 806 | Casetext Search + Citator) (Stephen v. Enterprise Rent-A-Car, 235 Cal.App.3d 806 | Casetext Search + Citator).)

Orders Granting Class Certification: In contrast to denials, an order granting class certification does not qualify for the death knell exception because it does not terminate the action for anyone. Instead, it allows the case to proceed on a class basis. Such an order is considered a typical interlocutory ruling that generally must await final judgment before appellate review. Defendants (or objecting parties) do not have an automatic right to immediately appeal a class certification grant (Litigating on the Fault Line: Class Action Law in California — Impact Fund). The case will usually continue through litigation, and any challenges to the class certification (e.g. arguing the class should not have been certified) can be raised in an appeal from the final judgment. For example, if the defendant loses at trial or faces an adverse judgment in a certified class action, it can argue on appeal that the class should never have been certified, as a ground for reversing or decertifying. But there is no appeal as of right before final judgment for a certification order that keeps the lawsuit alive.

Interlocutory Review by Writ (Discretionary Review)

Although a defendant (or sometimes a plaintiff in a partial-denial scenario) cannot appeal a class certification order as of right (absent the death knell situation), interlocutory review is still possible through California’s extraordinary writ procedure. A party may file a petition for a writ of mandate (or prohibition) asking the Court of Appeal to review and overturn the trial court’s class certification ruling before the case goes to final judgment. This is an extraordinary remedy, and the appellate court has discretion on whether to grant such review – it is not guaranteed. In fact, California appellate courts exercise this discretionary review sparingly in class action matters (Litigating on the Fault Line: Class Action Law in California — Impact Fund).

A writ of mandate is essentially a request for the appellate court to intervene mid-stream on the grounds that the trial court abused its discretion or acted unlawfully in certifying or decertifying a class. Because class certification decisions are committed to the trial court’s discretion, appellate courts are hesitant to intervene absent a compelling reason. Typically, the petitioner (usually a defendant challenging a granted class certification) must demonstrate that waiting for final judgment would cause irreparable harm or undue burden, or that the class ruling presents an important legal question that merits immediate resolution. There is no formal rule (akin to Federal Rule 23(f)) in California state practice that sets specific criteria, but courts have drawn guidance from similar considerations: for example, whether the class ruling poses a “death knell” for one of the parties (e.g. exerting overwhelming pressure to settle), whether there are novel or unsettled questions of law, or clear errors that would waste resources if not corrected early (Appellate Court Provides Valuable Guidance for Interlocutory Appeals of Class Certification Orders Under Rule 23(f)) (Appellate Court Provides Valuable Guidance for Interlocutory Appeals of Class Certification Orders Under Rule 23(f)). Ultimately, the Court of Appeal has “unfettered” discretion in granting or denying a writ petition, and most petitions are summarily denied without detailed explanation (Appellate Court Provides Valuable Guidance for Interlocutory Appeals of Class Certification Orders Under Rule 23(f)) (Appellate Court Provides Valuable Guidance for Interlocutory Appeals of Class Certification Orders Under Rule 23(f)). A denial of a writ petition does not imply approval of the trial court’s ruling on the merits; it simply means the appellate court chose not to exercise immediate review. (The party can still raise the issue in a later appeal from final judgment, since a writ denial generally has no res judicata effect on the issues.)

In practice, writ relief in class certification cases is rare. California Supreme Court decisions illustrate that only exceptional cases justify mid-stream review. Sav-On Drug Stores, Inc. v. Superior Court, for example, was a case in which the defendant sought appellate review after class certification was granted; the Court of Appeal had granted a writ and reversed the class certification, but the California Supreme Court then accepted review and ultimately upheld the class certification, emphasizing the trial court’s broad discretion (Litigating on the Fault Line: Class Action Law in California — Impact Fund) (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). This underscores that writ review will be granted only when there is a strong showing of error or an important issue – routine class certification rulings are left undisturbed until final judgment.

It is worth noting that California’s approach contrasts with federal court practice. Federal Rule of Civil Procedure 23(f) explicitly allows a party to seek permission for an interlocutory appeal of a class certification order within 14 days, and the federal appellate courts have discretion to accept or decline the appeal (Litigating on the Fault Line: Class Action Law in California — Impact Fund). California has no directly analogous rule, but the combination of the death knell doctrine (for plaintiffs facing class denial) and the writ of mandate procedure (largely used by defendants challenging class grants) serves a similar function (Litigating on the Fault Line: Class Action Law in California — Impact Fund) (Litigating on the Fault Line: Class Action Law in California — Impact Fund). The writ process is discretionary like the federal 23(f) petition, but California emphasizes that such discretionary intervention is to be granted only in exceptional circumstances (Litigating on the Fault Line: Class Action Law in California — Impact Fund).

Appellate Standards of Review for Class Certification Decisions

Whether on direct appeal (after a death-knell order or final judgment) or on a granted writ, California appellate courts apply a highly deferential standard when reviewing a class certification decision. The standard of review is abuse of discretion (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). The trial court’s ruling on class certification will be upheld so long as it was supported by substantial evidence and founded on correct legal criteria (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). Because trial judges are considered “ideally situated to evaluate the efficiencies and practicalities of permitting group action,” they are afforded broad discretion in deciding whether the criteria for class treatment are met (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). An appellate court will not overturn a class certification ruling “unless (1) improper criteria were used or (2) erroneous legal assumptions were made.” (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator) In other words, a clear error of law or usage of incorrect legal standards constitutes an abuse of discretion. But if the trial court applied the proper criteria and its decision is supported by any reasonable justification, the appellate court will defer to the trial court’s judgment (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). “Any valid pertinent reason stated will be sufficient to uphold the order.” (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator) This abuse-of-discretion review applies equally to orders granting or denying class certification. For example, a Court of Appeal reviewing a death-knell appeal of a class denial will ask if the trial court abused its discretion in finding the class criteria unsatisfied; likewise, if a defendant appeals a class certification after final judgment (or via writ), the question is whether the trial court abused its discretion in certifying the class.

It’s important to note that within this deferential framework, certain aspects can involve de novo review of legal issues. If the appeal raises a pure question of law – such as the interpretation of a statute as it affects class suitability, or whether the trial court applied an incorrect legal standard – the appellate court will review that legal issue without deference. But the ultimate decision to certify or not is reviewed for abuse of discretion, meaning factual determinations and the balancing of interests by the trial court are given great weight (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). The California Supreme Court in Linder v. Thrifty Oil Co. and Sav-On Drug Stores reaffirmed that appellate courts should not substitute their own judgment for the trial court’s as long as the proper criteria were applied. This deference is intended to prevent “piecemeal” appeals and to recognize the trial court’s vantage point in managing class actions (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). Consequently, when an appellate court does accept review of a class certification decision (either via death knell or writ), the hurdle to reverse the trial court’s decision is high – only a manifest abuse of discretion or legal error will justify reversal (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator).

Procedural Requirements for Appealing Class Certification Decisions

The procedure for initiating appellate review of a class certification order depends on the route of review (appeal as of right versus writ petition). In all cases, timing and proper filings are critical to invoke appellate jurisdiction. Below is an overview of the steps and deadlines:

  • Notice of Appeal (Death Knell or Final Judgment): If a class certification order is immediately appealable (either under the death knell doctrine for a denial of class cert, or as part of a final judgment in the case), the party must file a timely notice of appeal in the superior court. Under California Rules of Court, Rule 8.104, a notice of appeal in a civil case generally must be filed within 60 days after the superior court clerk or a party serves the notice of entry of the judgment or appealable order, or within 180 days after entry of the order if no notice of entry was served (Rule 8.104. Time to appeal | Judicial Branch of California). This deadline is jurisdictional – an appeal filed late will be dismissed (Rule 8.104. Time to appeal | Judicial Branch of California). The notice of appeal is a simple document identifying the order or judgment being appealed (e.g. “the order denying class certification entered on [date]”). In a death knell scenario, the 60-day clock typically starts when the order denying class certification is filed and served. The appellant should be careful to specify the correct order and follow all formatting requirements of Rule 8.100 (e.g. including the names of parties, the court, etc.). Once the notice is filed, the case proceeds in the Court of Appeal on a regular briefing schedule. (The appellant must also pay the filing fee and designate the record on appeal – usually a clerk’s transcript or appendix and any reporter’s transcript of the class certification hearing, as needed to show what happened in the trial court.)
  • Petition for Writ of Mandate (Interlocutory Review): To seek discretionary review of a non-appealable class certification order (for example, a defendant challenging an order granting class certification), the proper mechanism is to file a writ petition in the Court of Appeal. There is no fixed statutory deadline for a writ petition, but it must be filed within a “reasonable time” – and in practice, sooner is better. Parties often aim to file within the 60-day window analogous to a normal appeal, or even within a few weeks of the order, to strengthen the argument that prompt intervention is needed. The writ petition is a more elaborate filing than a notice of appeal: it should include a petition (often verified) explaining the case background, the relief sought, and why the trial court’s order was an abuse of discretion or legal error; a memorandum of points and authorities citing legal authority; and an appendix or exhibits containing the pertinent documents (the class certification order, the motion papers, and any relevant evidence from the record). The petition must also demonstrate why the normal appeal after final judgment would be inadequate – this is a crucial element. Typically the petitioner will argue that the class order will cause irreparable harm or unnecessary expense if not corrected immediately, or that important rights are at stake (for instance, the cost of class litigation might force a defendant to settle regardless of merits, or a plaintiff’s small claim will not proceed without class mechanism). The petition is filed directly in the Court of Appeal (with proof of service on the trial court and other parties). It is also common to simultaneously file a request for an immediate stay of trial court proceedings (such as staying notice to the class or the ongoing litigation) while the writ is under consideration. The opposing party may file a preliminary opposition in the appellate court if invited or may simply wait to see if the court requests an opposition or issues an alternative writ. If the Court of Appeal is inclined to consider the matter, it may ask for opposition (and sometimes hold oral argument) before deciding whether to grant the writ. If the writ is granted, the appellate court will issue a writ directing the trial court to vacate or modify its class certification order (or occasionally, the appellate court might simply treat the writ petition as an appeal and decide the issue on the merits). If the writ is denied (which often occurs without detailed comment), the trial court’s order stands and the case continues in the trial court; the petitioner’s only recourse at that point is to proceed to final judgment and then appeal, or to seek discretionary review in the California Supreme Court (which is rarely granted at this interim stage).
  • Discretionary Review by the California Supreme Court: In exceptional instances, a party may seek review in the California Supreme Court either after the Court of Appeal’s decision on a class certification issue or directly via an original writ petition. Generally, the Supreme Court becomes involved only after the Court of Appeal has acted (for example, if the Court of Appeal published an opinion on a death knell appeal or granted a writ and decided the merits). The aggrieved party can file a petition for review to the Supreme Court within 10 days after the Court of Appeal’s decision becomes final (Rule 8.500). The Supreme Court’s review is entirely discretionary and is usually reserved for cases presenting significant legal questions or needing resolution of conflicts in the law. Historically, the California Supreme Court has taken up class certification cases to clarify standards (e.g., Linder v. Thrifty Oil Co., Sav-On Drug Stores, Brinker Restaurant Corp. v. Superior Court), but this occurs in only a small fraction of cases. For most class certification disputes, the Court of Appeal’s disposition (or lack of interlocutory review) will be the end of the road until any final judgment appeal.

In summary, appealing a class certification order in California requires careful attention to the available pathways. If the order truly sounds the “death knell” for the class, an immediate appeal as of right is available – but it must be timely pursued (Litigating on the Fault Line: Class Action Law in California — Impact Fund). Otherwise, the party must either continue litigating to final judgment and appeal then, or attempt the uphill battle of a writ petition for interlocutory relief. Throughout the process, California’s appellate courts apply a deferential standard, upholding the trial court’s decision absent a clear error or abuse of discretion (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator). This framework – grounded in case law (e.g. Daar, Richmond, Stephen, Linder, Baycol) and a few key procedural rules – balances the need to protect class litigants’ rights with the policy against piecemeal appeals. It allows truly case-ending class certification rulings to be reviewed immediately, while generally discouraging premature appeals in the many class actions that proceed toward a final judgment.

Sources:

  • Code Civ. Proc. § 904.1 (appealable judgments and orders) (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group)
  • Daar v. Yellow Cab Co. (1967) 67 Cal.2d 695, 699 (origin of death knell doctrine) (Stephen v. Enterprise Rent-A-Car, 235 Cal.App.3d 806 | Casetext Search + Citator)
  • Richmond v. Dart Indus., Inc. (1981) 29 Cal.3d 462, 470 (class certification order appealable if it effectively dismisses class claims) (Litigating on the Fault Line: Class Action Law in California — Impact Fund)
  • Stephen v. Enterprise Rent-A-Car (1991) 235 Cal.App.3d 806, 811 (appeal from class denial must be taken immediately or is waived) (Litigating on the Fault Line: Class Action Law in California — Impact Fund)
  • In re Baycol Cases I & II (2011) 51 Cal.4th 751, 758-759 (California Supreme Court articulating death knell requirements: de facto final judgment for class, and remaining claims too small to ensure later review) (Miranda v. Anderson Enterprises, Inc., 241 Cal.App.4th 196 | Casetext Search + Citator)
  • Munoz v. Chipotle Mexican Grill, Inc. (2015) 238 Cal.App.4th 291, 309-310 (death knell doctrine inapplicable where PAGA representative claims remained, giving plaintiff incentive to continue) (“Death Knell” Doctrine Does Not Apply When PAGA Claim Remains In Trial Court)
  • Miranda v. Anderson Enterprises, Inc. (2015) 241 Cal.App.4th 196, 200 (death knell doctrine applies to dismissal of class claims; sets two-part test and notes it can apply to PAGA dismissal when individual arbitration compelled) (Dismissal of Claims for “Death Knell” Doctrine – Matern Law Group) (Miranda v. Anderson Enterprises, Inc., 241 Cal.App.4th 196 | Casetext Search + Citator)
  • Sav-On Drug Stores, Inc. v. Superior Court (2004) 34 Cal.4th 319, 326, 330-332 (class certification orders reviewed for abuse of discretion; trial court’s decision will not be disturbed if it was based on proper criteria and substantial evidence) (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator) (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator)
  • Linder v. Thrifty Oil Co. (2000) 23 Cal.4th 429, 435-436 (improper to deny class certification based on merits or damages considerations; reaffirming deferential review standard) (Sav-On Drug Stores, Inc. v. Superior Court, 34 Cal.4th 319 | Casetext Search + Citator).
Continue Reading
Click to comment

Leave a Reply

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *

Noticias

Soy un entrenador personal. Chatgpt me construyó una rutina de movilidad de 15 minutos para las caderas más sueltas, y me sorprende los resultados

Published

on

Como entrenador que ha estado viendo ChatGPT y AI se vuelven cada vez más prominentes en la industria del fitness, quería ponerlo a prueba. No es la primera vez: le pedí a Chat GPT que construyera un programa de entrenamiento de 4 semanas hace un tiempo, y tuve emociones mixtas sobre los resultados.

Más de dos años después, e incluso más adelante en la línea de desarrollo de IA, decidí ponerlo a prueba nuevamente. Esta vez, pedí una rutina de movilidad de la cadera de 15 minutos que pudiera hacer desde casa usando solo una de las mejores esteras de yoga como equipo. Le expliqué que me considero hacia el extremo avanzado de la escala de movilidad y dejo que haga lo suyo.

Continue Reading

Noticias

Ai ahora ‘en la cúspide de hacer una nueva ciencia’

Published

on

[Image created via OpenAI’s image generation technology]

“Estamos en la cúspide de sistemas que pueden hacer una nueva ciencia”.

Esa línea, en la página 3 del último “Marco de preparación” de OpenAI (versión 2, actualizada el 15 de abril de 2025), señala un posible cambio de paradigma para el ecosistema de I + D, que rápidamente está pasando de ser una etapa interna ansiosa, si no siempre precisa, a una colega potencial de AA, o incluso un investigador principal.

Mirando hacia el futuro, el marco lidia con el potencial de la IA para convertirse en “mejorando recursivamente”. Advierte que la “aceleración importante en la tasa de IA I + D” podría introducir rápidamente nuevas capacidades y riesgos. Esta aceleración podría superar las medidas de seguridad actuales, haciendo que la supervisión sea “insuficiente” y marcando explícitamente el peligro de perder el “mantenimiento del control humano” sobre el sistema de IA.

Hablando en un evento de Goldman Sachs solo unas semanas antes, el 5 de marzo (lanzado el 11 de abril en YouTube), la directora financiera de Operai Sarah Friar reforzó este punto de vista, afirmando que los modelos ya están “presentando cosas novedosas en su campo” y superando simplemente reflejando el conocimiento existente para “extender eso”. Friar señaló además el rápido enfoque hacia la inteligencia general artificial (AGI), lo que sugiere “Podemos estar allí”.

Si bien reconoce el debate en curso con algunos expertos que se balancean incluso en el término AGI y mucho menos su viabilidad, al menos con modelos de idiomas grandes), Friar mencionó la opinión del CEO Sam Altman de que la inteligencia general artificial (AGI), la IA que maneja el trabajo humano más valioso, podría ser “inminente”. Esto sugiere que la transición de la IA como herramienta para los investigadores de la IA como investigador puede estar más cerca de lo que muchos se dan cuenta, con primeros ejemplos potencialmente emergentes en campos como el desarrollo de software.

https://www.youtube.com/watch?v=2kzqm_bue7e

Las principales instituciones de I + D están construyendo activamente capacidades de ‘investigación autónoma’. Por ejemplo, los laboratorios nacionales como Argonne y Oak Ridge están desarrollando ‘laboratorios autónomos’ diseñados específicamente para la ciencia y la química de los materiales. Los Alamos también está trabajando con OpenAi
Probar sus modelos de razonamiento en Energía y Aplicaciones de Seguridad Nacional en su supercomputadora de Venado.

En general, los laboratorios nacionales están explorando el uso de IA para asumir tareas de investigación básicas: generar hipótesis (a menudo a través de estrategias de optimización), diseñar experimentos de varios pasos, controlar la ejecución robótica, analizar los resultados en tiempo real e iterando hacia objetivos de descubrimiento con una intervención humana significativamente reducida dentro de dominios operativos específicos. Si bien aún requiere supervisión humana para la validación y la dirección estratégica, que funciona quizás en un ‘nivel 3’ o ‘nivel 4’ emergente de la autonomía de la investigación, tales iniciativas demuestran que la IA se va más allá del análisis de datos pasivos para participar directamente en el proceso de descubrimiento científico. Esto se extiende más allá de la construcción de sistemas integrados; Implica empoderar directamente a los investigadores, como se ve en el reciente Doe ‘1,000 científico Ai Jam’. Esta colaboración a gran escala reunió a unos 1.500 científicos en múltiples laboratorios nacionales, incluido Argonne, para probar modelos avanzados de razonamiento de IA de compañías como OpenAi y Anthrope en problemas científicos del mundo real. Los investigadores exploraron específicamente su potencial para mejorar las tareas como la generación de hipótesis y la automatización del experimento.

Una transición similar ya está en marcha en el desarrollo de software, aunque los desarrolladores actualmente tienen vistas mixtas sobre el potencial de las herramientas habilitadas para Genai. La IA de hoy a menudo sirve como asistente, pero la tecnología está aumentando rápidamente su juego de software, especialmente para lenguajes comunes que van desde Javascript hasta Python. Los modelos de OpenAI están demostrando un progreso significativo, “acercándose a nivel humano” en puntos de referencia clave, y Fray señaló que uno ya es “literalmente el mejor codificador del mundo”. Esto respalda el potencial fraile descrito para un “ingeniero de software de agente”, una IA que “puede salir y trabajar de forma independiente para usted”, incluidas la construcción, las pruebas y las aplicaciones de documentación. Esta evolución hacia capacidades más autónomas podría remodelar el campo por completo.

AI de 5 niveles de Openai
marco de madurez

Según los informes, Operai utiliza un marco interno de cinco niveles para comparar su progreso hacia la inteligencia general artificial (AGI). Esta estructura, discutida dentro de la compañía a mediados de 2024 y luego informada por puntos de venta como Bloomberg, describe distintas etapas de capacidad de IA:

  1. Nivel 1: Chatbots / AI conversacional: Sistemas expertos en el lenguaje natural, como Chatgpt.
  2. Nivel 2: razonadores: AI capaz de resolver problemas básicos comparables a un humano altamente educado. En este nivel, los modelos también pueden demostrar habilidades de razonamiento emergentes sin herramientas externas.
  3. Nivel 3: Agentes: Sistemas de IA autónomos que pueden administrar tareas complejas y tomar decisiones durante períodos prolongados en nombre de los usuarios.
  4. Nivel 4: Innovadores: La IA contribuye significativamente a la creatividad y el descubrimiento generando ideas novedosas, ayudando a la invención o impulsando los avances.
  5. Nivel 5: Organizaciones: La etapa del ápice donde la IA puede gestionar y operar las funciones complejas de toda una organización, potencialmente excediendo la eficiencia humana.

En general, los laboratorios nacionales están explorando el uso de IA para asumir tareas de investigación básicas: generar hipótesis (a menudo a través de estrategias de optimización), diseñar experimentos de varios pasos, controlar la ejecución robótica, analizar los resultados en tiempo real e iterando hacia objetivos de descubrimiento con una intervención humana significativamente reducida dentro de dominios operativos específicos. Si bien aún requiere supervisión humana para la validación y la dirección estratégica, que funciona quizás en un ‘nivel 3’ o ‘nivel 4’ emergente de la autonomía de la investigación, tales iniciativas demuestran que la IA se va más allá del análisis de datos pasivos para participar directamente en el proceso de descubrimiento científico. Esto se extiende más allá de la construcción de sistemas integrados; Implica empoderar directamente a los investigadores, como se ve en el reciente Doe ‘1,000 científico Ai Jam’. Esta colaboración a gran escala reunió a unos 1.500 científicos en múltiples laboratorios nacionales, incluido Argonne, para probar modelos avanzados de razonamiento de IA de compañías como OpenAi y Anthrope en problemas científicos del mundo real. Los investigadores exploraron específicamente su potencial para mejorar las tareas como la generación de hipótesis y la automatización del experimento.

Una transición similar ya está en marcha en el desarrollo de software, aunque los desarrolladores actualmente tienen vistas mixtas sobre el potencial de las herramientas habilitadas para Genai. La IA de hoy a menudo sirve como asistente, pero la tecnología está aumentando rápidamente su juego de software, especialmente para lenguajes comunes que van desde Javascript hasta Python. Los modelos de OpenAI están demostrando un progreso significativo, “acercándose a nivel humano” en puntos de referencia clave, y Fray señaló que uno ya es “literalmente el mejor codificador del mundo”. Esto respalda el potencial fraile descrito para un “ingeniero de software de agente”, una IA que “puede salir y trabajar de forma independiente para usted”, incluidas la construcción, las pruebas y las aplicaciones de documentación. Esta evolución hacia capacidades más autónomas podría remodelar el campo por completo.

Continue Reading

Noticias

Lo que se puso bien y mal

Published

on

Han pasado casi 30 años desde que fui a Disney World. Mis recuerdos de Disney son felices, pero no recuerdo ningún detalle más allá de usar oídos, hacer que los personajes firmen mi libro especial de autógrafos y permanezcan despierto hasta tarde para ver el espectáculo de fuegos artificiales en Epcot.

Tengo dos hijas, casi 4.5 y 2.5, que están obsesionados con las princesas, por lo que cuando descubrí que mi familia estaría en Orlando durante unos días en junio, decidí buscar ir a Disney World por el día. Haremos un viaje más grande de Disney World en un par de años, pero los niños menores de 3 años son gratuitos (una de las pocas cosas que sabía sobre Disney), así que pensé que aprovecharíamos eso y les daríamos una gran sorpresa.

El único problema es que pensar en planificar un día en Disney es abrumador. Hay Tanta información Acerca de cómo optimizar su tiempo en los parques.

Decidí pedirle a ChatGPT que planifique mi día, y luego tuve a Mary Helen Law, propietaria de la compañía de planificación de Disney Minnie Mouse Counselors y uno de los principales especialistas en viajes de Conde Nast Traveler, revise el itinerario. Siga leyendo para escuchar qué chatgpt se hizo bien y mal y qué tenía que decir un experto en Disney.

Conocer al experto

Mary Helen Law, fundador de Mini Mouse Counselores

Mary Helen es una madre y experta en viajes. Comenzó su carrera como agente de viajes en 2018 mientras trabajaba en marketing y desarrollo de negocios. En 2019 decidió dejar su trabajo diario para expandir su negocio. Desde entonces, ha ayudado a cientos de familias a planificar vacaciones mágicas en todo el mundo y es uno de los principales especialistas en viajes de Conde Nast Traveler.

My Disney World Chatgpt Planning de planificación

Primero, aquí está el aviso que le di a Chatgpt para crear nuestro itinerario de Disney World:

¿Puedes planificar el día de mi familia en Disney World? Seremos yo, mi esposo y mis dos hijas. Serán 2.5 y 4.5 para el viaje, y aman a Ariel, Elsa y Ana, Moana, Belle, 101 Dalmatians, Cenicienta y Mary Poppins.

Nos gustaría ir a dos parques diferentes en el transcurso del día, pero necesitaremos un descanso de tres a cuatro horas en la mitad del día para una siesta. Nos gustaría hacer un almuerzo sentado en un restaurante temático que nuestras niñas les gustaría en función de sus intereses. ¿Puede planificar un itinerario para el día para los parques que recomendaría? Además, debe haber una parada de bocadillos por la mañana y la tarde.

¿Qué chatgpt hizo lo correcto sobre la planificación de un viaje a Disney World?

Hay muchas cosas que ChatGPT se equivocó sobre la planificación de un viaje a Disney (más sobre eso en un momento), pero sí recomendó paseos y actividades que encajarían bien en función de los intereses de mis hijas, como ir al viaje “Under the Sea” y conocer a Ariel, ver “cuentos encantados con Belle”, con un almuerzo en el restaurante de invitados y ver la festival de la fantasía de Magic Kingdom.

Cuando mi hermana usó un planificador de Disney el año pasado, tuvo la experiencia opuesta. El planificador acaba de recomendar todos los paseos más populares, como Tron, en el que mi sobrino no habría tenido interés, por lo que al menos Chatgpt prestó atención a lo que le dije que le gustaban a mis chicas.

También le pregunté a ChatGPT si tenía algún consejo para tener un día exitoso en Disney, y obtuve una buena información, como usar la aplicación de Disney para verificar los tiempos de espera de viaje y pedir comida con anticipación, y que podríamos usar el programa Rider Switch en caso de que mi hijo menor fuera demasiado pequeño para viajar.

También me dio algunas recomendaciones excelentes sobre qué empacar para el día, como protector solar, toallitas para bebés y bocadillos. Law estuvo de acuerdo en que había algunas pepitas de buena información, pero señaló que ChatGPT no incluía empacar un cargador de teléfono portátil, algo que dijo que necesitaríamos.

Qué chatgpt se equivocó sobre nuestro itinerario del día de Disney

Tres cosas principales para recordar sobre ChatGPT es que solo responde a lo que le da, se está retirando de la información en Internet y puede que no siempre sea correcto, y tampoco hay un elemento humano para ayudar a racionalizar la información.

Por ejemplo, le dije a ChatGPT que quería ir a dos parques, por lo que me dio un itinerario basado en ese aviso. Nunca hubiera sugerido que no haga dos parques porque sería poco realista dadas las edades de mis hijos.

ChatGPT carece de la capacidad de decir que no o sugerir ideas alternativas

Chatgpt hizo lo que le pedí, pero si hubiera abrazado las sugerencias, supongo que nunca habríamos regresado al parque después de una siesta y está muy frustrado.

Law, por otro lado, echó un vistazo a mi aviso y me dijo que realmente recomendaría no saltar en el parque y que deberíamos quedarnos en Magic Kingdom todo el día versus tratar de irme y volver.

Law me explicó que debido a que no nos quedamos en un resort de Disney, pasaremos mucho más tiempo pasando del estacionamiento a los parques, y que mi estimación de 30 minutos probablemente fue más como una hora y media. ChatGPT no sabe cuánto tiempo lleva llegar al estacionamiento y regresar a un hotel y no pudo estimar con precisión la logística detrás de esto.

También recomendó una siesta de cochecito en el carrusel de progreso con aire acondicionado, que según ella generalmente era un lugar más tranquilo, en lugar de tratar de irse y volver al parque. ChatGPT también recomendó este lugar y el Salón de Presidentes actualmente cerrado como un gran lugar para tomar un descanso, pero en general necesitaba un humano con más conocimiento de cómo funcionan las cosas en Disney para ayudarme a entender lo que era realista en lugar de no para nuestro viaje.

Chatgpt no incluyó ningún tiempo de espera para los paseos

Si nos fijamos en el itinerario que Chatgpt me dio por Disney, es como si tuviéramos el parque para nosotros mismos. Según ChatGPT, estaríamos en camino o en una nueva atracción cada 30 minutos.

Incluso sé lo suficiente sobre Disney para saber que eso no sonó bien. Law dijo que probablemente estaríamos en el extremo inferior de los tiempos de espera desde que iremos a principios de junio, pero acordamos que la cantidad de cosas que el itinerario dijo que logramos no parecía realista.

En cambio, ella me acompañó a través de la aplicación de Disney y me mostró cómo podré ver cuáles son los tiempos de espera para cada viaje, cuáles son los tiempos de show y cómo ver qué personajes están.

También me habló de las otras formas en que podemos reducir los tiempos de espera comprando pases de rayos o el pase Premier, que es un programa más nuevo (aunque costoso) que Disney está probando que le da una entrada a cada experiencia de Lightning Lane.

Usar ChatGPT sería excelente para preguntar qué paseos serían apropiados para mis niñas en función de su edad e intereses para que tengamos una idea de qué apuntar durante todo el día, pero la información sobre cómo usar la aplicación para ahorrar tiempo que la ley me dio será mucho más útil. También ayudó a establecer el nivel de mis expectativas sobre lo que podremos lograr en un día, lo que me ayudará a no estresarse por no poder hacerlo todo una vez que lleguemos allí.

Chatgpt se equivocó con cosas importantes que habrían arruinado nuestro día en Disney

Recuerde, soy un novato en Disney, así que tomé toda la información que me dio al pie de la letra.

El problema, dice Law, es que “ChatGPT simplemente no puede mantenerse al día con la cantidad que cambia Disney”. Se extrae de fuentes en todo Internet y no puede discernir lo que es correcto o no, así que terminé con cosas en el itinerario que no son precisos.

¿Uno de los mayores errores? El itinerario dijo que podríamos conocer a Ana y Elsa, los personajes favoritos de mis niñas, en el Princess Fairytale Hall, que no es cierto. Se encuentran y saludan en Epcot en el Royal Sommerhus.

Law sintió mi decepción y me aseguró que las chicas podrían saludar a Ana, Elsa y Olaf en la feria de amistad mágica de Mickey o en el desfile de Magic Kingdom.

¿Otras cosas importantes que Chatgpt se equivocó que habría descarrilado nuestro día? Sugirió conocer a Ariel a las 9 am cuando no está disponible hasta las 10 de la mañana; dijo que podríamos ingresar al parque a las 8 a.m., lo cual es incorrecto teniendo en cuenta que Magic Kingdom abre a las 8:30 a.m. para las personas que permanecen en la propiedad y las 9 a.m. para las personas que se mantienen fuera de la propiedad; y dijo que deberíamos usar Genie+ o un paso rápido para reducir los tiempos de espera, los cuales son servicios que ya no existen.

Es fácil suponer que lo que ChatGPT escupe es exacto, pero en nuestro caso todos estos errores habrían causado una frustración significativa para el día.

¿Debería usar ChatGPT para cualquier parte de su planificación de Disney?

Law dijo que podía ver que ChatGPT era útil para “cosas de espectro muy amplio” al planificar un viaje a Disney, como recomendaciones para qué recurre para quedarse o tener una idea general de qué personajes son los parques (aunque tenga en cuenta, ChatGPT me dio información incorrecta sobre esto).

“Creo que hay mucha seguridad laboral en lo que [travel planners] Haga por las relaciones que tenemos y el conocimiento “, dice, pero dice que no cree que sea una mala idea usar ChatGPT para obtener algunas ideas iniciales antes de hablar con un planificador.

Chatgpt Disney World Itinerario
Fuente: @mrscofieldandco | Instagram

¿Debería usar un planificador de Disney para su viaje de Disney?

No tiene que usar un planificador de Disney para planificar su viaje, pero después de mi experiencia con ChatGPT, usaré uno, ya que todavía no sé por dónde comenzar con toda la información.

Trabajar con un planificador de Disney es a menudo gratuito, ya que Disney le paga a una comisión al planificador, pero si no es así, podría valer la pena la inversión solo para asegurarse de obtener la información más precisa.

Si no desea usar un planificador, pregúntele a los amigos que hayan estado en Disney para sus consejos e itinerarios. Puede ser más fácil entender lo que es realista en lugar de no para su familia si tiene hijos de edad similar y aún reducirá el trabajo para usted (Everymom también tiene consejos de mamás para viajar a Disney World con niños pequeños, Disney con un bebé e incluso Disney World mientras está embarazada).

Veredicto final? ChatGPT podría ser bueno para algunos aspectos de la planificación de viajes, pero el itinerario que me dio en base a mi aviso no era realista y tenía muchos errores. Para algo tan complicado como Disney World, tener ideas y juicio humanos se siente como una mejor manera de tratar de garantizar más magia de Disney que los dolores de cabeza.

Elliot Harrell SHOYSHOT

Sobre el autor

Elliott Harrell, escritor colaborador

Elliott es madre de dos niñas y tiene su sede en Raleigh, NC. Pasa sus días dirigiendo un equipo de ventas y lavando la ropa y sus noches escribiendo sobre las cosas que ama. Le apasiona todas las cosas de la maternidad y la salud de las mujeres. Cuando no está trabajando, escribiendo o criando, puede encontrarla probar un nuevo restaurante en la ciudad o trabajar en su último proyecto de aguja.

Continue Reading

Trending