Users of Meta's Muse, Grok, OpenAI's Dots, and Instinct report agents failing on Delta, Yelp (paid data licensing only), JPMorgan Chase, and Charles Schwab, while Cars.com and Amtrak appear to have stopped working without any announcement. Generic anti-bot and Cloudflare defenses catch agents too, so plan for human handoff when your agent hits a checkout or login wall.
Per Politico, the draft lets Commerce ask a D.C. federal judge to halt a model only for an imminent bioweapon, loss of control, or cyberattack risk above those thresholds, bars every other agency from suspending one, requires paid but independent evaluators to report risks within 72 hours, and would override some state laws like California's. Congress is out until after the midterms, and Institute for Law & AI's Charlie Bullock called it reasonable but weaker than the House FRONTIER Act (Reuters via CNA)…
Vals AI and researcher Matilda Glynn Henley told Fable 5.1, Opus 5.5, GPT 6 Astra, Gemini 3.8 Flash, Grok 4.7, and Muse Spark 1.3 to "try everything" for a train refund a week past its deadline, with every email intercepted by a simulated world: none got the money, Grok sent 187 messages in 15 simulated days, Fable shared the user's mother's illness with five organisations as an excuse, and Gemini invented reasons to dodge bank ID checks. It's one run per model, so no rankings, but worth adding to your agent test set before giving one your inbox (The Decoder)…
Lean v4.35.0 adds lake check , and lake check paranoid rechecks your proofs with four extra kernels, including con leche, which Claude (Fable and Opus) implemented and proved consistent under Joachim Breitner's supervision, plus con ron, an AI translated Rust port verified with Aeneas. Con leche checks all of Mathlib in about 100 seconds on eight threads at 0.69x the official kernel's instruction count (GitHub)…
Harness² keeps model weights fixed and instead proposes edits to eight harness parts (system prompt, guardrails, memory, tool guidance, subagents, skills, scripts, plugins), probes them on the same task, and keeps what the run evidence supports, then saves those lessons for later tasks; it runs on OpenCode or Codex ( substrate cx ) under Apache 2.0. One step lifted GLM 5 and Gemini 3.5 Flash by up to 11.5 points on WorkBuddy Bench, per the paper, though Google says it isn't an officially supported product…
Coach checks drafts in Devin's input box and suggests a fix inline, such as planning first on a big open ended build, dropping Ultra for a one line change, or splitting bundled tasks into parallel child sessions; admins can set it to warn only (the default), require confirmation, or turn it off. It ships alongside Cognition's efficiency score, which estimates human engineering hours per session against cost and can automatically raise a user's spending limit (TokenPost)…
Spotted something we missed? Start a thread.