Tools
at long lake, we've bought 40+ services businesses to build AI where work actually happens we're working on: - deploying agents to complete …
at long lake, we've bought 40+ services businesses to build AI where work actually happens we're working on: - deploying agents to complete knowledge work - frontier eval generation from real workflow
at long lake, we've bought 40+ services businesses to build AI where work actually happens we're working on: - deploying agents to complete knowledge work - frontier eval generation from real workflows - post-training open models on data no lab has come build with us @llmh Media
Related
- “Valued work per watt is the score” @rolandgvc with the real details of self improving agents at @aiDotEngineer!
- Will be giving a talk titled “You should do RL for long-running agents (and use RLMs)” at 4pm on Sat at AI Engineer Singapore. Excited to se…
- 'Reality: The Final Eval' — 現実タスク完了率こそが最終評価指標（@swyx / Andon Labs）。 複数のAI実装を並列で回していると、実感として正確だと思う。SWE-Benchの数字より「本番で動くか」が判断軸。エージェント設計で最初に決めるの…
Source: Swyx (X) | 2026-09-09