Taylor Hornby 🛡❤️@DefuseSecSep 4Fine-tuning isn't a good argument for god, it's a better argument for anti-realism. We'd expect our models to have fitted, tuned parameters if what we're doing is compressing empirical data that was generated by a different model.4385
Taylor Hornby 🛡❤️@DefuseSecAug 25I understand left-hand and right-hand but where is my before hand?22551
Taylor Hornby 🛡❤️@DefuseSecAug 15I open-sourced some Claude agent definitions, which pretty much fully automate a security audit: GitHub - defuse/auditicianFrom github.com51517118K
Taylor Hornby 🛡❤️@DefuseSecAug 5Put a 100% wet reverb in parallel to the dry signal then add an LFO to the reverb. Plays the same role as a delay but sounds sooo much cooler.371K
Taylor Hornby 🛡❤️@DefuseSecJul 6Can someone please make a security issue severity grading bechmark so that AIs can get better at it?121.1K