
Sign up to save your podcasts
Or


In this episode, we talked with Ahmad Beirami, an ex-researcher at Google, to discuss various topics. We explored the complexities of reinforcement learning, its applications in LLMs, and the evaluation challenges in AI research. We also discussed the dynamics of academic conferences and the broken review system. Finally, we discussed how to integrate theory and practice in AI research and why the community should prioritize a deeper understanding over surface-level improvements.
By Ravid Shwartz-Ziv & Allen Roush5
44 ratings
In this episode, we talked with Ahmad Beirami, an ex-researcher at Google, to discuss various topics. We explored the complexities of reinforcement learning, its applications in LLMs, and the evaluation challenges in AI research. We also discussed the dynamics of academic conferences and the broken review system. Finally, we discussed how to integrate theory and practice in AI research and why the community should prioritize a deeper understanding over surface-level improvements.

6,881 Listeners

3,447 Listeners

3,072 Listeners

1,993 Listeners

1,105 Listeners

212 Listeners

7,244 Listeners

203 Listeners

313 Listeners

101 Listeners

551 Listeners

512 Listeners

602 Listeners

150 Listeners

147 Listeners