Poolside releases Laguna S 2.1 with 118B parameters and long-horizon coding focus
realsohamparekh · x · 2026-07-22
- Poolside announced Laguna S 2.1, a model with 118B total parameters and 8B active per token.
- The company says it performs well on agentic coding, can run on a single NVIDIA DGX Spark, and is unusually persistent on long-horizon tasks.
- A follow-up test in cyber-security environments found it finished tasks in under 20 minutes, while Kimi took nearly 3× longer.
- The tester noted accuracy trailed Kimi, but Laguna still did surprisingly well under strict verifiers, with finance environments to be tested next.
Related event: Poolside Releases 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from coding & agent
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- 9-year backend dev: AI code isn't the problem, the rate of making a mess is — Sweaty-Landscape-561 · 2026-09-11