About 30 LLM agents did a cosmology project with no human in the loop
You give it a sentence — “measure the cosmological parameters from this supernova dataset” — and walk away. About 30 language-model agents pick it up, search the literature, write the analysis code, run it, read the output, argue with each other about whether the answer is sound, and hand back a result. No human touches the keyboard in between. The team that built this calls the demo “a PhD level cosmology task,” and the system did it end to end. ...