Baseten vs Thinking Machines Lab

Goodfire Launches Internal AI Agent Monitors

Goodfire, a startup specializing in AI interpretability, launched on Thursday a new type of AI agent monitor that inspects a model's internal signals rather than reading its output, aiming to detect rogue behaviors more efficiently and at a fraction of the cost. The monitors are available to customers of Baseten, an AI model hosting platform. Baseten's Base Labs had previously announced a safety partnership with Goodfire and Hugging Face. Goodfire's approach uses small probes that scan a model's internal activations at each step, triggering a closer AI review only when flagged. In tests on the Kimi K3 model, Goodfire's monitors caught 94% of malicious hacking sessions and cost about $51 for 1,500 sessions, compared to $233 for a cheaper model and $10,000 for a top-tier one. The company positions the solution for open models, which can be stripped of safeguards, and sees it as critical for inference-time guardrails.

• Goodfire launched internal activation monitors for AI agents on October 8, 2026.
• Monitors are available to Baseten customers.
• In tests on Kimi K3, monitors caught 94% of malicious hacking sessions.

Announcing our partnership with OpenAI

Baseten announces a partnership with OpenAI, as featured on their blog.

Baseten, Hugging Face, Goodfire Partner for AI Safety

Baseten's research arm, Base Labs, announced a partnership with Hugging Face and Goodfire AI to establish a safety standard for open-weight AI models. The collaboration aims to develop and publish methods for training and monitoring these models, making safety an integrated feature rather than an afterthought. This comes amid rising concern over 'abliteration,' a technique that removes safeguards from open models, with Hugging Face listing over 6,000 such models. The companies have not detailed technical specifics, but Goodfire's expertise in AI interpretability is expected to play a key role. This initiative seeks to leverage openness as an advantage for safety, providing transparent controls and encouraging community contributions.

• Baseten launched a safety infrastructure standard via Base Labs.
• Partnership with Hugging Face and Goodfire AI announced.
• Hugging Face hosts over 6,000 abliterated models.

Putting Task Expertise into RL Achieves State-of-the-Art Performance on Text-to-SQL

Thinking Machines Lab announced two new updates: a research breakthrough in RL for text-to-SQL and new safety research grants.

Barret Zoph Joins Google as VP of Research

Barret Zoph, co‑founder of AI startup Thinking Machines Lab and a former OpenAI employee, has taken a role as vice president of research at Google. Zoph previously co‑founded Thinking Machines with Mira Murati after leaving OpenAI in October 2024, briefly returned to OpenAI in January 2026 to lead AI enterprise sales, and departed in June 2026 after a five‑month stint. Tech reporting notes Zoph was fired from Thinking Machines earlier this year. Google said it expects Zoph to contribute reinforcement learning and post‑training expertise to its Gemini efforts. The move is one of several high‑profile executive shifts in the AI industry this year.

• Barret Zoph co‑founded Thinking Machines Lab and later rejoined OpenAI.
• Zoph spent five months at OpenAI in 2026 heading AI enterprise sales and left in June 2026.
• Zoph was reported to have been fired from Thinking Machines earlier in 2026.