DSPy and GEPA users often write custom proposers to reduce overfitting
dbreunig · x · 2026-07-24
People using DSPy/GEPA often end up writing custom proposers to avoid overfitting and better tailor the proposer instructions to each task.
The author says they are trying a few ideas to make that easier and invites readers to check them out.
Related event: DSPy and GEPA Users Adopt Custom Proposers to Prevent Overfitting(2 posts)→
More from coding & agent
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11