overfeed.news
Anuncio

NexTalk

Automatiza la primera respuesta. Mantén el toque humano.

Chat en vivo con agentes de IA en tu modelo y tu clave de API, con traspaso a tu equipo.

Empezar gratis

Empresa

OpenAI

2610documentos

83últimos 7 días

OpenAI News

Introducing Astra for Law

OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.

en
AWS Machine Learning Blog

Improving HCLS AI reasoning with open-source agent skills

AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation steps, three worked use cases, and a 410-prompt evaluation showing a 70-86% win rate.

en
arXiv AI Papers

Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models

We evaluate six frontier language models on the two-agent (N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secretly chosen target using exactly _2 N yes/no questions. An answerer sees only the target and the question, and replies with one word. Both roles run on the same provider, so the game measures how well a model communicates with itself across an information asymmetry. We run 408 games over document sets of 4 to 1024 paragraphs at a total API cost of \$363. One model finishes well behind the others: Claude Opus 5 wins 28 of 68 games, against 45 to 56 for GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash and Kimi K3. The leading five are only marginally separable. Pooling those five, win rate declines with set size at r=-0.973 and is fit by a single per-round reliability parameter. The form is win=p^{_2 N} with p=0.928. Losses divide into answer errors and discrimination failures in roughly equal measure, and models almost never name a document their own evidence excludes. Every unanimous answer error from the weakest model was inspected: 32 of 34 are ``No'' answers, on properties stated in the document's first sentence, under an instruction that explicitly warns against defaulting to ``No''. Information per question, estimated from answer balance, correlates with win rate at r=+0.88. The only two models to extract a full bit per question are the only two that partition on document titles, a strategy absent below N{=}32 and used in a quarter of questions above it. Reasoning-token expenditure varies 4.5across models with little relation to success, and the trace grows as the candidate set shrinks without a matching gain in reliability.

en
arXiv AI Papers

How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents

Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to exponential improvements in performance with increases in computation. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly 20less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides increasing compute-efficiency gains, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale.

en
arXiv AI Papers

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents may need to infer behavior from working software and implement it in an incomplete application. We introduce ProgramDistill, a benchmark evaluating coding agents on features discovered through interaction with fully functional reference applications. We build ProgramDistill by factorizing applications into features of different granularities, each associated with replayable behaviors executable via its gold patch. Our pipeline, mine-craft-patch, discovers 1,975 replay-verified behaviors across 26 applications and constructs 4,063 tasks without human intervention. Across nine frontier coding agents, GPT-6 Astra and Claude Opus 5 achieve 49.2% and 28.8% success on cumulative workflows in full-application reconstruction. In partial-application reconstruction, success falls from 100% to 64.0% and from 96% to 32% as restoration depth increases from 1 to 8. ProgramDistill thus provides a scalable benchmark with controlled difficulty for evaluating and diagnosing coding agents, and a natural basis for future curriculum-based training.

en