Scobleizer meets GoodfireAI to discuss interpretability research and trust in LLMs
Scobleizer · x · 2026-08-04
In a reply, Scobleizer says he met the team behind GoodfireAI, a company focused on AI interpretability research. He describes the work as tearing apart LLMs to understand how they think and build trust in AI systems, and says the lunch was about the company and the state of the AI industry.
Related event: Scobleizer Meets GoodfireAI to Discuss LLM Interpretability(4 posts)→
More from Companies & People
- Users say OpenAI accounts tied to university emails cannot be transferred away — anshulkundaje · 2026-08-04
- One senior engineer plus AI agents can replace a five-person rebuild team — alex_verem · 2026-08-04
- A CS teacher says computer science is bigger than coding—and not dying — guzdial · 2026-08-04
- A Black Hat talk teases “Antares” for post-training and agentic training — aminkarbasi · 2026-08-04
- AI slop isn’t the model’s fault, the poster says—it’s the prompter — breath_mirror · 2026-08-04
- After a $1B profit quarter, Palantir CEO Alex Karp again attacks frontier AI labs — TechCrunch AI · 2026-08-04