Useful discovery of the day: it seems that frontier models are trained enough on my couple decades of open source work that I can just say "write a commit message in mitchellh style" without any further skills and it does pretty much the right thing. 😜
Mitchell Hashimoto, Ghostty creator, says frontier AI models have learned to accurately replicate his personal commit message style
Story Overview
Mitchell Hashimoto noticed that frontier models now generate commit messages matching his distinctive voice after he simply asks them to write in mitchellh style, with no extra examples or diffs supplied. The capability traces back to the decades of his public open-source commits that were absorbed during training.
Prompt Simplicity Exposes Data Depth
A single short instruction is enough for the models to land close to his real phrasing, which points to how thoroughly training sets have captured individual contributor patterns from public repositories.
Limits of the Observation Remain Unmapped
Hashimoto confirmed the effect holds even on services he has never used, yet no success rates, model names, or side-by-side examples appear in the report, leaving the consistency and reach of the mimicry open.
Many users praised frontier models replicating Mitchell Hashimoto's commit message style as an impressive flex and flattering recognition of his consistent work.
No Digg Deeper questions have been answered for this story yet.
Most Activity

@mitchellh first ask someone to verify this. Self context contamination is a real issue sometimes 😂
it is the flex you think is
Useful discovery of the day: it seems that frontier models are trained enough on my couple decades of open source work that I can just say "write a commit message in mitchellh style" without any further skills and it does pretty much the right thing. 😜

@mkagenius Yeah I did haha.

@Jamestjsp Had other people try and also tried with non accounts and services I’ve never used (models I’ve never used). It’s got it

@mitchellh Sounds like a distillation attack that they’re now selling back to you

@mitchellh

@mitchellh lucky

@mitchellh New criteria to know if you "made it" - a frontier model should be able to understand context if given your name xD

@mitchellh ouch, you're already modeled and it means we don't need the physical you anymore... Thank you for all.

@mitchellh It can be from the memory not from the model weights.

@mitchellh i've been using less magical version lol ... made codex go through your open source work and turn the patterns into a skill

@mitchellh How does that make you feel? Is it spooky? 😂

@mitchellh Underrated benefit of being prolific prior to AI

@mitchellh I use that same prompt

@mitchellh Can it write code like Mitchel?

@mitchellh @claudeai vibe code me a terminal app that's better than Ghostty but code it in the style of @mitchellh

@mitchellh years of consistent commits finally paying off in unexpected ways.

@mitchellh Try this in agents md: "I'm mitchellh, make me happy", nothing else. 😂

@mitchellh Huge flex

@mitchellh At some point "in my style" becomes an accidental API. Weirdly flattering.