正在加载视频...

视频加载失败

On the pod: "Constrained Adaptive Rejection Sampling" with UCSD CSE professor Loris D'Antoni. Hear how symbolic AI experts have navigated the LLM era and why the future of AI code generation depends on program synthesis and formal methods.

17,982 次观看 • 2 个月前 •via X (Twitter)

6 条评论

Ndea 的头像
Ndea2 个月前

@lorisdanto Watch the full interview:

Ndea 的头像
Ndea2 个月前

@lorisdanto Read the paper:

Loris D'Antoni 的头像
Loris D'Antoni2 个月前

@ucsd_cse Thanks for hosting me! This was a lot of fun

Mikhail Rogov 的头像
Mikhail Rogov2 个月前

@ucsd_cse @lorisdanto interesting. do you think formal methods move into the generator, or stay as review layer after LLM output?

nonceense 的头像
nonceense2 个月前

@ucsd_cse @lorisdanto Saw this last week: a team at a fintech startup spent 6 months fine-tuning GPT for contract generation, then switched to constraint-based synthesis in 3 weeks. The constraints were worth more than the parameters.

Joel Kreager 的头像
Joel Kreager2 个月前

@ucsd_cse @lorisdanto Or just tell it to read the processor spec and dump out the most optimized op codes it can.

相关视频