Name: 🎉 Happy to share my internship project Google DeepMind 🗼 – purely text-trained LLMs can act as evolutionary recombination operators 🦎 🧬 Our EvoLLM uses LLM backends to outperform competitive baselines. Work done w. Yingtao Tian & Yujin Tang 🤗 📜:
Uploaded: 2024-03-06T14:57:52.000Z
Duration: PT15.783S
Channel: Robert Lange
Description: Robert Lange shorts video about 🎉 Happy to share my internship project Google DeepMind 🗼 – purely text-trained LLMs can act as evolutionary recombination operators 🦎 🧬 Our EvoLLM uses LLM backends to outperform competitive baselines. Work done w. Yingtao Tian & Yujin Tang 🤗 📜:

🎉 Happy to share my internship project Google DeepMind... show more

Robert Lange

39,076 Aufrufe • vor 2 Jahren

Our work on AI to improve cyclone prediction is... show more

Jeff Dean

29,276 Aufrufe • vor 1 Jahr

LLMs, trained only on text, might already know more... show more

Sophie Wang

67,822 Aufrufe • vor 9 Monaten

Our AI financial agent now shows its thinking Much... like how Perplexity shows its tasks Here is how it works: • we have two LLMs • LLM #1 receives raw user query • LLM #1 creates tasks to answer query • LLM #2 receives these tasks • LLM #2 uses tools to execute tasks • LLM #2 streams answer to you We can add a 3rd LLM to do the last step. This would let LLM #2 focus only on task execution. I will add this in a follow-up. The code is open source so you can see how everything is done.show more