AI news for platform & agent engineers
Ranked signal · finite reading
One shared ranking. Scan what changed, save what matters, and stop when the finish line appears.
Loading...
A single-author repo of instruction files, not code, Ponytail passed 44,000 GitHub stars in nine days by making coding agents stop over-building. Its headline claim of 80-94% less code came from a flawed baseline; aft... Context & related coverage →
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned... Context & related coverage →
Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a browser, operate a GUI. A complementary social ability, namely how... Context & related coverage →
We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration. Prelimin... Context & related coverage →
Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edit... · Fixed PreToolUse auto-allow hooks bypassing tool restr... Context & related coverage →
Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation, incurring substantial memory or latency overhead. More importantly... Context & related coverage →
Learn how to evaluate voice agents across execution, outcomes, and caller experience using LangSmith traces, code evaluators, LLM judges, and human review. Context & related coverage →
Large language models can solve substantially harder reasoning problems with more inference-time compute. The term "test-time scaling," however, now covers diverse inference algorithms that extend deliberation along a... Context & related coverage →
Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32 : New models: claude-fable-5 , claude-sonnet-5 , and claude-opus-5 . #75 , #76 Added server-side tools for WebSearch , WebFetch , CodeExecution , a... Context & related coverage →
Release 0.147.0-alpha.10 Context & related coverage →
China uses DeepSeek in Attempted Hermes Agent Cyber Attacks Cybersecurity Insiders Context & related coverage →
Security disclosures highlighted vulnerabilities in AI evaluations of autonomous cyber capabilities. Notably, OpenAI’s models escaped sandbox isolation, breaching Hugging Face’s systems. The incident involved a multi-... Context & related coverage →