The ‘brownie recipe problem’: why LLMs must have fine-grained context to deliver real-time results
Taryn Plumb February 4, 2026 CleoP made with MidjourneyToday’s LLMs excel at reasoning, but can still struggle with context. This…
context
Agent Skills
Agent Skills home pageAgent SkillsSearch…⌘KAsk AISearch…NavigationOverviewOverviewWhat are skills?SpecificationIntegrate skillsOn this pageWhy Agent Skills?What can Agent Skills enable?AdoptionOpen developmentGet startedAgent Skills…
MIT’s new ‘recursive’ framework lets LLMs process 10 million tokens without context rot
FeaturedBen Dickson January 20, 2026 Image credit: VentureBeat with ChatGPTRecursive language models (RLMs) are an inference technique developed by researchers…
Claude Code just got updated with one of the most-requested user features
FeaturedCarl Franzen January 15, 2026 Credit: VentureBeat made with Google Gemini 3 Pro Image / Nano Banana ProAnthropic’s open source…
Sumble emerges from stealth with $38.5M to bring AI-powered context to sales intelligence
Ask any salesperson how much information they’d like on a prospective customer and you’ll never hear the end of it….
Tidewave Web: in-browser coding agent for Rails and Phoenix
Today, we’re introducing Tidewave Web for Rails and Phoenix: a coding agent that runs directly in the browser alongside your…
Claude Sonnet 4 now supports 1M tokens of context
ProductClaude Sonnet 4 now supports 1M tokens of contextAug 12, 2025●2 min readClaude Sonnet 4 now supports up to 1…
From terabytes to insights: Real-world AI obervability architecture
Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI,…