Benchmarking AI ghostwriting in your voice: 4 LLM judges, 9 metrics, and anti-slop tips
lmoroney · x · 2026-10-23
A Towards AI talk (shared by Louis-François Bouchard) built a benchmark testing whether models can write video scripts in Louis-François Bouchard's voice: 10 scripts, 5 drafts per model, 4 LLM judges, 9 metrics, and 1,000 human A/B checks. Notable finding: LLM judges favor their own model family. Practical tips: long prompts stuffed with your own writing samples, one review pass from a strong model, many cheap drafts merged, and always a final human edit.
More from coding & agent
- Perplexity ships Decider for Mac, running its 4B decision model locally with no API key — perplexity_ai · 2026-10-23
- Developer runs 5 parallel AI agent sessions to root multi-brand cameras into a Frankenstein surveillance system — aniketapanjwani · 2026-10-23
- Testing Hermes Agent with n8n: Letting Agents Execute Real Automation Workflows — techlatest_net · 2026-10-23
- OpenAI: Keep MCP Server Instructions Under ~1,000 Characters or ChatGPT May Truncate Them — bibryam · 2026-10-23
- Only ~56% of MCP Servers Provide Instructions, OpenAI Data Shows — bibryam · 2026-10-23
- OpenAI: Don't Hide MCP Tools Behind listCommand/executeCommand Dispatchers — bibryam · 2026-10-23