AI Gateway adds confidence-based decision fallbacks[AINews] Reflection Beam - 501B-A23B American Open ModelOpenAI “rogue” agent activities found on Wikimedia projectsHow Jump Trading is scaling quant research with ChatGPTThoughts from San FranciscoEmbeddingGemma 2: an open, lightweight multimodal embedding modelBuilding Git infrastructure for agent-scale developmentSharing AI progress in mathematicsv2.1.292rust-v0.161.0v2026.10.1-beta.2Training Numerical Intelligence via Auto-Diagnosis and Skill DiscoveryQuoting Victoria KimPenguin Mail – open-source Rust email client for Linux with AIREACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracersllm-mistral 0.16Advancing computer use with IroncladUtah to let AI examine patients and prescribe medication without human oversightProxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-ProbabilitiesEmbeddingGemma 2AI Gateway adds confidence-based decision fallbacks

AI Gateway can now escalate a decision request to a fallback model when the primary model’s answer trips a confidence condition you set. Conditions can be combined, so an escalation can depend on more than one signal. The plain model names you already list in models keep catching outright errors, so

A small win for US open source

OpenAI “rogue” agent activities found on Wikimedia projects Given how tempting a target wikis are for rogue agent swarms, it’s not a huge surprise that Wikipedia found evidence of that activity once they went looking: The Wikimedia Foundation conducted its own investigation to see whether Wikimedia

Jump Trading uses OpenAI to expand quantitative research. See how longer-running AI workflows combine multiple data sources with human review.

Agents.md in Google Docs

基于你关注的「ChatGPT Claude Deepseek Gemini 」主题，我们整理了最新动态与关键观点，建议在 中文 语境下快速浏览并追踪来源。

We’re rebuilding GitHub’s Git infrastructure while GitHub keeps running, creating a foundation for agent-scale software development. The post Building Git infrastructure for agent-scale development appeared first on The GitHub Blog .

https://github.com/openai/math https://github.com/openai/math/tree/main/preprints Comments URL: https://news.ycombinator.com/item?id=49984923 Points: 282 # Comments: 243

近期更新：v2.1.292；v2.1.291。What’s changed Added –marketplace to claude plugin install : adds the marketplace if needed, under the same policy checks as claude plugin marketplace add , then installs the plugin from it Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for Added

近期更新：v2026.10.1-beta.2；release-publish/91236e8c9501-1791331026: fix(ui): terminal disappears when docking from bottom to right (#166213)。OpenClaw 2026.10.1-beta.2

arXiv:2610.03872v1 Announce Type: new Abstract: AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underlyi

Since the Medicare breach, OpenAI has put in place additional monitoring to allow “immediate intervention” by staff to stop training if the company’s models access the internet in ways they’re not supposed to, Mr. Kwon [chief strategy officer at OpenAI] said. — Victoria Kim , Reporting from th

Article URL: https://penguin-mail.com/ Comments URL: https://news.ycombinator.com/item?id=49984716 Points: 30 # Comments: 9

arXiv:2610.03888v1 Announce Type: new Abstract: Reconstructing global sea surface pH from sparse observations is critical for monitoring ocean acidification and understanding marine carbon cycling. Traditional assimilation and inverse models are physically grounded but costly for large-scale reconst

Release: llm-mistral 0.16 Adds support for reasoning models, such as the newly released Mistral Large 4 . Tags: llm , mistral , llm-reasoning

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

Article URL: https://www.techspot.com/news/114111-utah-become-first-state-ai-examine-patients-prescribe.html Comments URL: https://news.ycombinator.com/item?id=49981197 Points: 54 # Comments: 83

arXiv:2610.03894v1 Announce Type: new Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong – by the time the error surfaces, the action has run. Frontier chat APIs hide the model’s token probabilities; the agent’s stated confidence barely beats chance on the

My comment on EmbeddingGemma 2 — Hacker News. I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license. For embedding models in particular, I don’t think it makes sense to use a closed, proprietary, hosted-only model. Most applications of embedding models involve calculating t