Telling agents their token throughput in the prompt improves time forecasting
maksym_andr · x · 2026-11-04
New AgentTime result: adding a single line to the forecast prompt stating the model's throughput speed (from Artificial Analysis) noticeably improves time-forecasting quality for GPT and Muse. Models naturally underestimate their own speed, so making throughput explicit corrects the bias, and agents generally predict shorter periods as a result.
A counterintuitive, one-line prompt-engineering finding: explicit token speed in the prompt meaningfully improves how well agents forecast their own execution time.
More from coding & agent
- HeyGen's HyperFrames skill turns text into editable MP4 videos in Perplexity — toolstelegraph · 2026-11-04
- mlx-serve PR runs DeepSeek-V4.1 tensor-parallel across two Macs, 57% faster decode — HankYeomans · 2026-11-04
- GitHub Copilot lands in JetBrains Air with local and cloud agent tasks — mariorod1 · 2026-11-04
- Scobel built a GrokBot watching 15,000 sources, polling election news every 30 minutes — Scobleizer · 2026-11-04
- Intent launches: large-scale coding agent coordination for developers on macOS — Wattenberger · 2026-11-04
- UserProof pipes live user session recordings into Claude Code to auto-fix conversion blockers — doooyle · 2026-11-04