Google says Antigravity and Gemini 4 Argon ported the core of a Fortran ocean model to safe Rust
Google's Antigravity team says an agent moved FVCOM's core solver into 13 safe-Rust modules in 59 minutes, and points to its migrate-to-rust skill.
Topic · 174 stories · page 2 of 8
174 stories tagged agents on AI Tamer, newest first.
Google's Antigravity team says an agent moved FVCOM's core solver into 13 safe-Rust modules in 59 minutes, and points to its migrate-to-rust skill.
zg, a local hybrid search tool for coding agents from the zvec team, rebuilt its core pipeline in Rust. Its own M3 Pro test shows faster indexing, less memory.
SolidCraft 0.30.1 fixes three advisories: an agent permission bypass, a lock-file symlink overwrite and an API key check skipped with '#'. Upgrade now.
Anthropic's message threads beta keeps a conversation server-side for 5 minutes, so agent loops send only new messages. Prices unchanged; not ZDR eligible.
GitHub-verified MCP servers are in public preview for all Copilot plans: 26 services, no local install. Business and Enterprise admins must opt in.
Updated 9 November: Meituan released LongCat-2.5 weights on Hugging Face under MIT. Deployment docs cover NPUs only. API price was $0.30/$1.20 per million.
Tencent says agent-created database instances grew over 80x in a year, with 1 million active, and added branching and faster serverless scaling.
A Google-led paper builds a 4.1K-sample benchmark for implicit and changing requests. Every model tested gets worse as interactions run longer.
dsh-superagent runs on DeepSeek Harness, takes work from allowed people on GitHub and answers with a PR. MIT, research code. What its docs say.
The Rust SSH library's advisories reached GitHub's global database this weekend, so Dependabot will flag them. Every russh before 0.65 is affected.
Ramen VR's Autopilot plays your game from a prompt, writes its own test harnesses and remembers your levels. Apache-2.0, Windows and macOS.
Vercel Labs' Rust CLI gives agents snapshots and refs for any app on macOS, Windows and Linux, headless by default. What 1.0 changes and the privacy catch.
Microsoft's Apache-2.0 4B agent model chooses GUI actions or shell commands each turn and reports 66.0% on 361 OSWorld-Verified tasks.
yoagent 0.26.0 keeps MCP HTTP redirects on the server's origin so custom key headers stay put; 0.26.1 keeps URL keys out of error text.
OpenAI explained its four-layer misalignment monitoring. Tool-using Responses API traffic is watched too, with auto-pause and webhooks.
OpenAI's 29 October Model Spec reorganizes around five values, adds context and oversight rules, retires most style guidance and renames the assistant GPT.
Eight changes from our past week for people building with AI: two security fixes, a new default, a hosted shutdown and new tools, each with a next step.
Mistral's stateless /v1/responses endpoint returns the answer, reasoning and tool calls as separate items, for its hosted chat models including Large 4.
Pro plans get API credits equal to their price; Business pools $20 or $100 per seat, capped at $500. Credits expire each cycle and exclude Codex.
Quarry checks whole agent sessions, not single prompts, for risky sequences like a credential read followed by an upload. Apache-2.0, with a CLI and SDK.
In a 50-analyst trial, a coin flip set Claude's preference on each judgment call. Analysts matched it 86% of the time and rarely credited the agent.
Amazon's memo to engineers says token counts and AI adoption are flawed targets but useful measures. It asks for outcomes, and judgement on where AI helps.
Surge AI tested agents on 50 realistic tax assignments. The leader, Claude Sonnet 5.5, passed 10.8% at a 95% rubric bar. Missed deadlines were common.
Index v5 puts 60% of its weight on private or held-out tests. Claude Opus 5.5 led at launch with 58; the best open-weights model trailed by 12.