ProCreations/betterwright-agent-traces
Viewer • Updated • 3.84k • 83 • 2
SSH PRO
ProCreations
AI & ML interests
i make stuff
Recent Activity
posted an update about 8 hours ago
auto 200m 2 is out now!
Auto is a series of models designed to classify if a tool called by an AI agent is safe to run or not, like how the "auto" approval modes work in codex or claude. This is the smallest model in the series by far and it still packs a punch! Over 96 percent accuracy on the held out benchmark, beating deepseek v4 0731 and absolutely destroying regex at classifying if a tool call is safe to run (to be fair it is a bit of a weird and very hard benchmark but it works!)
check it out: https://huggingface.co/ProCreations/auto-200m-2
updated a collection about 8 hours ago
Auto Series liked a model about 11 hours ago
ProCreations/auto-200m-2Organizations
