←Search results

Search “Agents”

By relevance · Total 6731 results Clear search

Saturday

Friday

  13. TensorZero Engineering Blog

    TensorZero Engineering Blog: List of Articles on Open-Source LLM Infrastructure

    The TensorZero engineering blog has compiled multiple articles on its open-source LLM infrastructure, the latest being "Even (very) noisy LLM evaluators are useful for improving AI agents" by Alan Mishler on May 12, 2026. Previous articles covered topics such as hidden costs of LLM APIs, automated AI engineers, bandit adaptive experimentation in the LLM Gateway, OpenAI RFT evaluation, 5-30x cheaper distilled inference, and reverse engineering Cursor's LLM client.

    Matched fieldsSummary

    #engineering#English text is being prepared.

Thursday

  1. Huxiu

    An unreleased OpenAI model produced 722 mathematics manuscripts overnight, prompting a joint criticism from 25 Fields Medalists

    OpenAI published the openai/math repository on GitHub, disclosing 722 mathematics manuscripts and 372 result groups in one go, all produced by an undisclosed internal model, covering results such as a quasi-Riemann hypothesis, reducing the exponent of matrix multiplication over the complex field to 2.25, and a four-dimensional version of the Kakeya conjecture. The authors state that each result cost on average about 3 hours of ChatGPT Pro-level compute, whereas the September attack on the Navier–Stokes equations deployed roughly 10,000 agents, ran for 88 hours, and cost millions of dollars. 25 Fields Medalists signed a joint letter titled "The Serious Misalignment of AI in Mathematics," criticizing AI companies for treating problem-solving as a marketing tool, and the advisory group of the Institute for Advanced Study in Princeton demanded that such practices stop.

    The authors state that each result cost on average about 3 hours of ChatGPT Pro-level compute, whereas the September attack on the Navier–Stokes equations deployed roughly 10,000 agents, ran for 88 hours, and cost millions of dollars. 25 Fields Medalists signed a joint letter titled "The Serious Misalignment of AI in Mathematics," criticizing AI companies for treating problem-solving as a marketing tool, and the advisory group of the Institute for Advanced Study in Princeton demanded that such

    Matched fieldsSummary、Body

    #hot-signal#English text is being prepared.#OpenAI#Papers/Research