Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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.

18,106 Aufrufe • vor 3 Monaten •via X (Twitter)

6 Kommentare

Profilbild von Ndea
Ndeavor 3 Monaten

@lorisdanto Watch the full interview:

Profilbild von Ndea
Ndeavor 3 Monaten

@lorisdanto Read the paper:

Profilbild von Loris D'Antoni
Loris D'Antonivor 3 Monaten

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

Profilbild von Mikhail Rogov
Mikhail Rogovvor 3 Monaten

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

Profilbild von nonceense
nonceensevor 3 Monaten

@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.

Profilbild von Joel Kreager
Joel Kreagervor 3 Monaten

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

Ähnliche Videos