Claude Code

Mitchell Bryson AI Reliability Articles · August 10, 2026 00:00

The permission prompt is giving way to the blast wall - Mitchell Bryson

Claude Code is making auto mode the default, Docker is shipping disposable sandboxes for agents, Wardline is auto-blocking compromised agents, and TechCrunch is warning that AI safety tests can become safety risks. The shared story is that builders are...

Topics: Safety Evals

Entities: Safety EvalsClaudeClaude Code

Mitchell Bryson AI Reliability Articles · May 07, 2026 00:00

The night shift nobody asked for - Mitchell Bryson

Three announcements share a thread that should make builders take notice: AI that works when nobody's watching. Anthropic's 'dreaming' lets agents learn from their own mistakes between sessions, Claude Code Routines ship finished PRs while developers sleep,...

Entities: AnthropicClaudeClaude CodeGoogleGoogle DeepMind

METR Blog · February 17, 2026 08:00

Analyzing coding agent transcripts to upper bound productivity gains from AI agents

Amy Deng investigates whether coding agent transcripts could serve as an alternative for estimating AI productivity uplift, using 5305 Claude Code transcripts from METR technical staff.

Entities: ClaudeClaude Code

METR Blog · February 13, 2026 08:00

Measuring Time Horizon using Claude Code and Codex

Nikola Jurkovic describes our measurements of time horizon using Claude Code and Codex scaffolds.

Entities: ClaudeClaude Code