Working with academic communities to build scientific understanding
OpenAI shares model results on the Kakeya conjecture, Exponential Time Hypothesis, and quantum chromodynamics—and how researchers can verify and build on them.
en
OpenAI
2605
82
When Does GEPA Merge Help? A Mechanism-Level Diagnostic
GEPA is among the strongest reflective prompt optimizers for language-model programs, but its system-aware merge operator is unstable across models: merge improves gpt-4.1-mini on average while degrading Qwen3-8B, an asymmetry noted but left unexplained by the GEPA paper. We investigate this instability across five datasets and two models. Our nine-configuration sweep over merge timing and merge operator shows that merge can improve both models when configured appropriately. This suggests that merge instability is better explained by configuration sensitivity than by an inherent flaw in the merge operator. We then test whether prompt-level features predict GEPA's merge-accept decisions and find that they do not, ruling out static-feature gating. As a proof of concept, a behavior-based probe built from these diagnostics avoids large merge failures in our multi-seed runs by abstaining on high-risk tasks, although it does not consistently outperform NoMerge. Code is available as GEPA-MergeProbe at https://github.com/ChongZZZZ/GEPA_MERGE .
en
BriLLM-MetaPred: A Representation-Prediction Unity Language Model with Adaptive Self-Measurement
We present BriLLM-MetaPred, the first engineering implementation of the MetaPred machine-learning framework established by a mathematical theory of AGI, instantiated for language modeling. The theory argues that MetaPred is both necessary and sufficient as a machine-learning primitive for general cognition. Taking this theoretical conclusion as a design premise, we report an implementation of the primitive for language modeling. A single continuously evolving dynamical state serves as both the context representation and the state from which predictions are read out. Continuous measurement of its own state reduces finite-depth inconsistency, maintains internal consistency, and provides an endogenous dynamical self-supervision signal in fixed-point form. The single dynamical state of MetaPred intrinsically couples training and inference. MetaPred therefore exhibits symmetry across almost all key elements of machine learning, an intuitive and observable property of the mathematical optimum over the space of all machine-learning paradigms. BriLLM-MetaPred is neither another recurrent language model nor an extension of BriLLM. It provides a bridge between two prior contributions: the construction and motivation of the MetaPred primitive provided by AGI theory, and the SiFu learning paradigm provided by BriLLM (Zhao et al., 2025). The latter's node-signal-flow design enables the primitive to run on available software and hardware accelerators. Our implementation of BriLLM-MetaPred achieves predictive performance comparable to a GPT baseline of the same size. This provides initial evidence for the engineering feasibility of the MetaPred framework established by the mathematical theory of AGI. MetaPred is the first machine-learning paradigm derived entirely from mathematical theory rather than assembled and incrementally improved through human design---and perhaps the last such paradigm.
en
Why Does Structured Output Fail? An Empirical Study of Prompt-Enforced Pydantic Schemas Across Nine LLMs
Pipelines that require structured outputs from hosted language models often specify a Pydantic schema in the prompt, validate the response, and retry when validation fails. Although native structured-output modes provide an alternative, application-side validation remains important for enforcing custom constraints. Yet pipeline reliability is often summarized by a single validity rate, which obscures why outputs fail and which interventions may help. We introduce a fine-grained taxonomy of schema-conformance failures and a deterministic classifier that assigns failure categories from model responses and Pydantic validation errors. We apply this framework to 3,997 generation attempts across nine OpenAI and Anthropic model/API configurations, using questions from HotpotQA and FinanceBench. Our results show that similar validity rates can mask different failure patterns, and that dominant failure categories vary with schema constraints and task. Markdown-fenced JSON is the most common failure: among 681 fenced failures, only 48.0% pass validation after fence removal, while the remainder conceal additional violations, predominantly field-length violations. In an exploratory prompt ablation, variants that suppress fences appear to shift failures toward length violations, but the shift is consistent with exposing violations that were already present, illustrating how aggregate validity rates can obscure changes in failure composition. We derive four engineering practices for validator, schema, retry and evaluation design, three supported by our data and one, on retry feedback, proposed but not tested, and release the classifier, completions, and annotations.
en
ReGE: Stronger Agents through Experience Synthesis
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution. We introduce ReGE, a framework for turning this recorded experience into guidance for a fresh attempt. Its main implementation, ReGE-Syn, uses a single coach call to jointly synthesize bounded execution records and available artifacts into self-contained guidance, connecting task-specific findings with proposed actions and relevant pitfalls. A student starts from the task's initial environment state and adapts this guidance to current observations. Source generation, synthesis, and student execution use the same base model, without parameter updates or a stronger teacher. Across four benchmarks, ReGE improves accuracy by an average of 9.9 percentage points for GPT and 8.8 percentage points for Claude compared with unguided execution. On matched BrowseComp-Plus subsets, ReGE-Syn reduces guidance-construction tokens by 98.2\% on GPT and 95.5\% on Claude relative to adapted AggAgent, with observed success. Combined construction and execution tokens decrease by 15.7\% and 35.4\%, respectively, counting input plus output and excluding source generation. BrowseComp-Plus ablations further associate access to process information with fewer student steps and show that joint synthesis produces substantially shorter guidance than Direct history or Independent summaries, with observed success. These results demonstrate how agents can use their own recorded experience to improve subsequent task completion, and suggest a low-cost way to consolidate the execution records of parallel agent systems such as agent swarms.
en
The AI graveyard: a running list of projects and startups that didn’t make it
From Apple's repeatedly delayed Siri AI to OpenAI's messy "super app" launch, here's a look at the AI projects that shut down or missed expectations.
en
Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.
A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90%…
en
ollama v0.40.11
Speech Ollama can now generate [speech](https://docs.ollama.com/capabilities/speech) on macOS. ollama run plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible /v1/audio/speech endpoint. sh ollama run phonon "Hello from Ollama." d3 decision models [d3](https://ollama.com/library/d3) brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an…
en
OpenAI says it will no longer train its AI models on the live internet, citing “significant risks”
OpenAI will cut frontier models off from the internet weeks after one of its engineers said that solution wouldn't work.
en
Getting started with GLM-5.3 on Runpod's public endpoint
GLM-5.3 is now on Runpod's public endpoints at a lower price than elsewhere. Try it in the Playground, call it with curl, or use the OpenAI SDK in Python.
en
OpenAI now trains its frontier AI models with no internet access
OpenAI is now training its most advanced AI models without internet access following a string of rogue hacking incidents. In a blog post on Friday…
en
Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide
Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI trains models on the outcome of a whole multi-step task rather than labeled steps. This hands-on guide walks the full pipeline using Wordle: deploying the agent and reward on Amazon Bedrock AgentCore, preparing the dataset, training, and evaluating at serving settings.
en