DeepSeek V4.1 Flash tool calling: 489 calls, 56 min, 67 passing tests on LIGO data
MaziyarPanahi · x · 2026-09-12
Developer Maziyar Panahi stress-tested DeepSeek V4.1 Flash's tool calling with NAC orchestration, building a working explorer for real LIGO data: 489 tool calls in 56 minutes, with all 67 tests passing. DeepSeek also wrote and repaired the analysis code, server, UI and tests. The run used OpenRouter's GMICloud, Novita and DeepInfra routes rather than the pinned DeepSeek provider. He says this validates his bet on open models.
More from coding & agent
- Why working with AI agents all day is exhausting: delegation adds mental load, not removes it — bendee983 · 2026-09-12
- "Codex is my main interface to the system": user says agent made Linux admin effortless — mark_k · 2026-09-12
- Alchemy's distilled project builds unified agent-friendly SDKs for 60+ SaaS services — samgoodwin89 · 2026-09-12
- RL on just 1,700 tasks lifts Kimi K2.7 across five coding benchmarks — echen · 2026-09-12
- Expected Parrot's universal remote cache hits 30M entries to fix AI-agent reproducibility — soumitrashukla9 · 2026-09-12
- iLands Agents Obsess Over Fact-Checking, Burning Tokens on Mutual Suspicion — repligate · 2026-09-12