Two years after Devin launched: Cognition's task success climbed from ~30% to 90%
silasalberti · x · 2026-09-05
A new interview revisits Cognition two years after Devin's launch, discussing its redemption arc: reliability improved from roughly 30% to 90% task success, enterprise adoption is expanding beyond tech companies, and fast inference helps developers stay in flow. Hosted by @MilksandMatcha with @silasalberti, presented with Cerebras.
More from coding & agent
- GPT Sol plays real-time table tennis via latency-aware agent research loop — wzenus · 2026-10-21
- Daytona raises $60M Series B at $1B valuation to build the agent cloud — tsi_org · 2026-10-21
- PostgreSQL 19 slips to November as LLM-assisted code review floods committers with edge cases — sanjaykalra · 2026-10-21
- 9x Vision open-sources video perception for agents: timestamped evidence via MCP and CLI — koto9x · 2026-10-21
- LangChain adds Human-in-the-Loop beta to Managed Deep Agents — LangChain · 2026-10-21
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21