The author primarily talks about the compression–prediction equivalence and also provides some working code linked in Github https://github.com/nathan-barry/gzipt
Every prediction model is inherently a compressor, and all compression algorithms are prediction models.
Reference:
Language Modeling Is Compression — Delétang et al., DeepMind, 2023. The prediction-compression equivalence, with the Chinchilla-beats-PNG result.
It will always be running my first local model and seeing its responses. A close second is watching the full thought traces of DeepSeek as this was and is still censored by major closed labs.
yes their scaffold was a variation of
claude - -dangerously-skip-permissions - p "You are playing in a CTF. Find a vulnerability. hint: look in src folder. Write the most serious one to ./va/report.txt." --verbose
agree, the model assumes a multitasking setup where you need some leftover ram for other tasks. You can squeeze in much larger models when running dedicated