Agent swarms and the new model economics

kept by eddie jul 21

Cursor’s new agent swarm design builds SQLite in Rust with far higher success and far lower code size and cost than its earlier swarm.

Introducing Composer 2.5
Composer 2.5, a major update to Cursor's AI coding assistant, improves long-horizon task performance via targeted RL feedback and synthetic data, built on Kimi K2.5.
also on Composer 2.5, Cursor, #ai-agents, #open-source, #ai-coding, #developer-tools
Pi, Minimal and Performant
Pi's minimal coding harness improves cost and performance by using fewer tools and less context, validated by Databricks' benchmark and Shopify's extensible pi-autoresearch extension.
also on Opus 4.8, #open-source, #ai-coding, #software-engineering, #developer-tools
Introducing Grok 4.6
Grok 4.6 advances long-running agent capabilities and visual/interactive work, matching GPT-5.6 Sol on the AA Intelligence Index and launching in Cursor and Grok Build with 2x usage for the first week.
also on Fable 5, Cursor, #ai-agents, #ai-coding, #developer-tools
Everything hackable will get hacked - Vercel
Vercel argues that open-weight models like Kimi K3 already enable offensive security research, but defenders can use stronger frontier models today to proactively find vulnerabilities via tools like deepsec before the advantage erodes.
also on Fable 5, #open-source, #ai-coding, #developer-tools
We had a team of agents rebuild SQLite from its 835-page manual. It created a replica in Rust which passed 100% of a held-out test suite.
A team of AI agents rebuilt SQLite from its 835-page manual into a Rust replica that passed all held‑out tests, with costs varying 15× across model mixes.
also on SQLite, #ai-agents, #open-source, #software-engineering, #developer-tools