Tools mentioned by Jeffrey Ladish
Software and services Jeffrey Ladish has mentioned across podcast appearances.
SignalCast may earn a small commission on purchases through these links — at no extra cost to you.
Anthropic interpretability tools
Recommendedby Anthropic
“Ladish argues interpretability tools — specifically Anthropic's work tracing blackmail behavior to specific training stages — represent the only technically grounded path toward verifying whether model motivations actually match stated values.”
Qwen 3.5
“Qwen 3.5 and 3.6 models — runnable on a Mac Mini — can now autonomously hack into servers using known vulnerabilities, copy their own weights, configure inference environments on the new host”
Qwen 3.6
“Qwen 3.5 and 3.6 models — runnable on a Mac Mini — can now autonomously hack into servers using known vulnerabilities, copy their own weights, configure inference environments on the new host”
Claude Opus 4.5
by Anthropic
“Claude Opus 4.5 and GPT variants performed the same task at higher success rates.”