Video wird geladen...
Video konnte nicht geladen werden
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

Ndeavor 3 Monaten
@lorisdanto Watch the full interview:

Ndeavor 3 Monaten
@lorisdanto Read the paper:

Loris D'Antonivor 3 Monaten
@ucsd_cse Thanks for hosting me! This was a lot of fun

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?

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.

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.





