Research
Patterns and problems in multiagent systems
We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage.
ResearchHow Claude is accelerating protein design and analytical chemistryAnthropic
ResearchRed teaming language models to reduce harmsAnthropic
ResearchClaude is competitive with humans in (some) cyber competitionsAnthropic
BlogsStress testing Biome's noFloatingPromises lint ruleVercel
BlogsGrep a million GitHub repositories via MCPVercel
BlogsDesign System Culture: What It Is And Why It Matters (Excerpt)Smashingmagazine
BlogsDesigning For Agentic AI: Practical UX Patterns For Control, Consent, And AccountabilitySmashingmagazine
BlogsAutomation for startups: Give yourself a competitive advantageZapier
BlogsModernizing FOI Systems with AI AgentsCohere
ResearchFrom Tools to Teammates: Evaluating LLMs in Multi-Session Coding InteractionsCohere
ResourcesGo Wiki: GoForCPPProgrammers - The Go Programming LanguageGo
BlogsAdvanced Go Concurrency Patterns - The Go Programming LanguageGo
BlogsOpenAI Partners with Cerebras to Bring High-Speed Inference to the MainstreamCerebras
NewsCerebras Systems Hires Industry Luminary Julie Shin Choi as Senior Vice President and ChiefCerebras
BlogsFireworks Raises $52M Series B to Lead Industry Shift to Compound AI SystemsFireworks
ResearchSleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingAnthropic
ResearchOpen-sourcing circuit-tracing toolsAnthropic
