DeepSeek V4-Pro's stop-control issue persists across scaffolds; 100M token test shows prompts don't fix it
karminski3 · x · 2026-08-16
Blogger karminski3 conducted 18 independent long-horizon agentic coding tests on DeepSeek-V4-Pro-0813, with up to 50 tool calls each, combining 3 scaffolds and 2 stop prompts, repeated 3 times, totaling 100M tokens. Conclusion: changing scaffolds or prompts does not fix the stop-control issue, which is independent of overfitting. In tests, the model called finish only 3 times, continued after completion 4 times, and many runs lacked full verification.
Related event: DeepSeek-V4 Pro Beats Rivals in Cost-Effective Benchmark(10 posts)→
More from coding & agent
- Dispatch launches newsletter infrastructure built for AI agents, one API call to publish — RichardsonDx · 2026-10-16
- Creator shares the agent-powered system behind millions of monthly impressions — VibeMarketer_ · 2026-10-16
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16