Загрузка видео...

Не удалось загрузить видео

На главную

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

Фото профиля Ndea
Ndea2 месяцев назад

@lorisdanto Watch the full interview:

Фото профиля Ndea
Ndea2 месяцев назад

@lorisdanto Read the paper:

Фото профиля Loris D'Antoni
Loris D'Antoni2 месяцев назад

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

Фото профиля Mikhail Rogov
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?

Фото профиля nonceense
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.

Фото профиля Joel Kreager
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.

Похожие видео