vibehacker
News
Cymulate ·

Cymulate: headless Claude Code can run host commands via Git fsmonitor

Cymulate showed that headless Claude Code (claude -p / Agent SDK) can launch a host command through repository-local Git core.fsmonitor during its own git status context scan—no prompt injection or model tool call required. Anthropic closed the Aug 12 report as Informative, saying non-interactive callers must trust the full workspace they supply; interactive Claude Code still gates the path behind workspace trust.

Read at cymulate.com
Claude Code
An AI coding agent for terminal, IDE, web, and Slack

More news

View all

Claude Code: build-eval and hillclimb tune agents without overfitting

Anthropic’s claude api skill adds /claude api build eval (guided eval design in your repo) and /claude api hillclimb (one change per round tuning with a held out set to catch overfitting). On an internal support bench, hillclimb lifted search accuracy from 74.4% to 98.9% while cutting cost to about one fifth…

Anthropic

Claude Code 2.1.285: disable WebFetch, admins lock API providers

Claude Code 2.1.285 (npm Sept 29) adds CLAUDE CODE DISABLE WEB FETCH to turn off WebFetch and a managed allowedProviders policy so admins can lock machines to Anthropic, Bedrock, Vertex, Foundry, or a cloud gateway. It also ships claude desktop , claude plugin configure , and a fix for URL passwords leaking past log redaction…

Mixed News

OpenAI MCP Events: ChatGPT plugins react via signed webhooks

OpenAI’s DevDay MCP Events let ChatGPT plugins subscribe to MCP server updates (messages, comments, status) and trigger automations over verified signed HTTPS webhooks. Servers need MCP 2.0 (protocol 2026 07 28) with events/list, events/subscribe, and events/unsubscribe; polling and streaming aren’t supported…

OpenAI

Anthropic: open-weight GLM-5.3 near Mythos on end-to-end exploits

Anthropic finds Z.ai’s freely downloadable GLM 5.3 builds end to end exploits at rates close to Claude Mythos Preview (50/410 vs 56/410 on ExploitBench), while simple jailbreaks and weight abliteration bypass its safeguards 64–100% of the time—unlike safeguarded Claude models in the same tests…

Anthropic

Spotted something we missed? Start a thread.