Posts
All the articles I've posted.
-
Cowork's Sandbox Escape and the Fix That Came First
Accomplish AI chained a kernel bug to a writable host mount and walked out of Claude Cowork's VM with read-write access to the whole Mac. Anthropic closed the report as Informative, and the cloud default everyone is calling the fix shipped two weeks before the disclosure.
-
Opus 5 Shipped and Hacker News Argued About a Computer Vision Pipeline
Claude Opus 5 arrived at Opus 4.8 prices with a #1 Intelligence Index ranking, and the 1,300-comment HN thread mostly skipped the benchmarks to argue about one demo anecdote. The pricing story has a documented counterexample.
-
PenClaw Sells a No-Refusals Pentester for $20 a Month. First You Show It Your Passport.
PenClaw rents a hosted OpenClaw tenant running an abliterated LLM as an autonomous pentester, advertised with 'No Limits. No Objections.' Every route to the model runs through a government ID check, a scope fence and an egress firewall. The guardrails moved from the weights to the account.
-
Anthropic Deleted 80% of Claude Code's System Prompt. Your CLAUDE.md Is Next.
Two guides published alongside Claude Opus 5 say most accumulated prompt-engineering folklore is now an anti-pattern: delete your verification steps, delete your examples, delete your rules. Here's what survives, and what the deletions cost you.