·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
PSA: Your Claude shared chats and Artifacts may have ended up on Google44m◆Microsoft launches its first cybersecurity model, plus a new agentic cybersecurity system2h◆OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.3h◆OpenAI’s Hugging Face breach has reignited the debate over alignment and control3h◆Why China is giving away its best AI models4h◆Threads users can now chat with Meta AI in their DMs4h◆Google’s AI search is rapidly becoming the default, new data shows5h◆Power up your AI infrastructure! A first look at the Smart Systems Stage agenda at TechCrunch Disrupt 20265h◆This $9 key physically locks your most addictive apps5h◆Ilya Sutskever’s Safe Superintelligence partners with Nvidia to scale its AI research6h◆Enigma raises $71M to make controlling a robot as easy as adjusting the volume8h◆Nvidia, Microsoft launch open AI security alliance — without OpenAI, Google, or Anthropic8h◆The path to artificial superintelligence9h◆Closing the data loop in AI-driven drug discovery9h◆Building the enterprise environment for agentic AI9h◆NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics11h◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models17h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders17h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA17h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging17h◆PSA: Your Claude shared chats and Artifacts may have ended up on Google44m◆Microsoft launches its first cybersecurity model, plus a new agentic cybersecurity system2h◆OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.3h◆OpenAI’s Hugging Face breach has reignited the debate over alignment and control3h◆Why China is giving away its best AI models4h◆Threads users can now chat with Meta AI in their DMs4h◆Google’s AI search is rapidly becoming the default, new data shows5h◆Power up your AI infrastructure! A first look at the Smart Systems Stage agenda at TechCrunch Disrupt 20265h◆This $9 key physically locks your most addictive apps5h◆Ilya Sutskever’s Safe Superintelligence partners with Nvidia to scale its AI research6h◆Enigma raises $71M to make controlling a robot as easy as adjusting the volume8h◆Nvidia, Microsoft launch open AI security alliance — without OpenAI, Google, or Anthropic8h◆The path to artificial superintelligence9h◆Closing the data loop in AI-driven drug discovery9h◆Building the enterprise environment for agentic AI9h◆NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics11h◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models17h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders17h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA17h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging17h◆
News/This startup’s new mechanistic interpretability tool lets you debug LLMs
mit-tech-review
PublishedApril 30, 2026 at 3:59 PM
—neutral

This startup’s new mechanistic interpretability tool lets you debug LLMs

Source
technologyreview.comfull article ↗
Read on mit-tech-review→
Publisher summary· verbatim

The San Francisco–based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters—the settings that determine a model’s behavior—during training. This could give model makers more fine-grained control over how this

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
mit-tech-review
Read original ↗All from mit-tech-review →

No replies yet. Be first.

Source
↗
mit-tech-review
Read original ↗All from mit-tech-review →

Related coverage

More from MIT-TECH-REVIEW
mit-tech-reviewOpenAI called the Hugging Face attack unprecedented. But we’ve been here before.3hmit-tech-reviewThe path to artificial superintelligence9hmit-tech-reviewClosing the data loop in AI-driven drug discovery9hmit-tech-reviewBuilding the enterprise environment for agentic AI9h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on mit-tech-review ↗
HomeModelsNews