GPT-5.6 Built a Tiny iMessage Transformer From One Prompt
Pietro Schirano says Sol generated the code, pipeline, tokenizer, training loop and local reply model in about 30 minutes.
By Ryan Merket · Published
Primary source: X
Why it matters
Schirano's demo shows frontier coding models moving from app scaffolding into local ML project generation, where the bottleneck shifts from writing code to controlling private data, evaluation and memorization risk.

Pietro Schirano (@skirano), the MagicPath CEO and builder behind early AI design tools, posted a thread on X on July 9th showing GPT-5.6 Sol generating a full training pipeline for a small language model trained on his iMessage history.
…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.