dmodel.ai
dmodel.ai · 102 words · saved by 2 readers
steerable and explainable AI
About d_model is a fundamental AI research lab partnering with frontier labs to turn their models into capable interpretability and alignment researchers. Alongside our partnerships, we aim to use the agents we build for independent research. Alignment is an unsolved problem with enormous stakes. We think that interpretability is key to making models safer and more steerable. We build RL environments for open-ended interpretability tasks. These environments teach agents how to do cutting-edge research, not how to reward-hack. You've already used LLMs trained on our environments. Help us…
saved by
related reading
- Goodfire AIgoodfire.ai
- Neuronpedianeuronpedia.org
- Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
- Foundation Models for Oversight | Transluce AItransluce.org
- A Pragmatic Vision for Interpretability — LessWronglesswrong.com
- Training Language Models to Explain Their Own Computationsarxiv.org
- RSI Simulator | Paradigmparadigm.xyz
- Interconnects AI | Nathan Lambert | Substackinterconnects.ai
- ARENA - AI Safety Curriculumlearn.arena.education
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
- Data lab to train frontier models & evaluate agents | micro1micro1.ai