Загрузка видео...
Не удалось загрузить видео
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 просмотров • 2 месяцев назад •via X (Twitter)
Комментарии: 6

Ndea2 месяцев назад
@lorisdanto Watch the full interview:

Ndea2 месяцев назад
@lorisdanto Read the paper:

Loris D'Antoni2 месяцев назад
@ucsd_cse Thanks for hosting me! This was a lot of fun

Mikhail Rogov2 месяцев назад
@ucsd_cse @lorisdanto interesting. do you think formal methods move into the generator, or stay as review layer after LLM output?

nonceense2 месяцев назад
@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 Kreager2 месяцев назад
@ucsd_cse @lorisdanto Or just tell it to read the processor spec and dump out the most optimized op codes it can.




