Prompting Claude Opus 5.5(platform.claude.com)

177 points by Michelangelo11 28 days ago | 191 comments

Anthropic's Claude Platform documentation page giving prompting guidance for Claude Opus 5.5, covering behavioral differences from Opus 5, effort calibration, thinking, and agentic tasks.

Claude: System Prompts(platform.claude.com)

727 points by tosh 2 months ago | 276 comments

Anthropic documentation page listing the core system prompts used by Claude on claude.ai and its iOS and Android apps, organized by model and date.

Speed up responses with fast mode(code.claude.com)

207 points by surprisetalk 8 months ago | 218 comments

Apple Foundation Models(platform.claude.com)

457 points by MehrdadKhnzd 4 months ago | 214 comments

Anthropic documentation for the Claude for Foundation Models Swift package, which lets Apple apps use Claude via Apple's Foundation Models framework LanguageModel protocol.

Claude Code SDK(docs.anthropic.com)

427 points by sync 1 year ago | 186 comments

Anthropic documentation page for the Claude Code SDK, which lets developers run Claude Code programmatically as a subprocess from their applications.

Orchestrate teams of Claude Code sessions(code.claude.com)

371 points by davidbarker 8 months ago | 202 comments

Claude Code documentation page explaining experimental agent teams, which coordinate multiple Claude Code sessions with shared tasks, inter-agent messaging, and a team lead.

Claude Fable 5(anthropic.com)

2521 points by Philpax 4 months ago | 2018 comments

Anthropic announcement post introducing two new AI models, Claude Fable 5 and Claude Mythos 5, dated June 9, 2026, with a linked system card.

Claude Fable is relentlessly proactive(simonwillison.net)

676 points by lumpa 4 months ago | 556 comments

Simon Willison blog post describing Claude Fable 5 as relentlessly proactive, illustrated with an example of fixing a scrollbar glitch in Datasette Agent.

Claude Fable 5: mid-tier results on coding tasks(endorlabs.com)

373 points by bugvader 4 months ago | 217 comments

Endor Labs blog post benchmarking Claude Fable 5 on 200 real-world coding tasks for its Agent Security League, reporting middling functional and security results.

Claude now has access to a server-side container environment(anthropic.com)

628 points by meetpateltech 1 year ago | 326 comments

Anthropic product announcement that Claude can now create and edit files such as spreadsheets and documents using a server-side container environment.

What it feels like to work with Mythos(oneusefulthing.org)

341 points by swolpers 4 months ago | 302 comments

Ethan Mollick's One Useful Thing post describing his early-access experience with Claude 5 Fable, the first publicly released Mythos-class AI model.

Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher(vals.ai)

1150 points by u1hcw9nx 1 month ago | 528 comments

Vals AI blog post reporting that Claude Fable 5.1 solved the Cyphral Distich, an unsolved cipher from 1653, within a day when given it as an open task.