Read on Twitter
Can we use LLMs for bug detection?
- compiler testing: generate programs
- "like" static analyzers:
* what is wrong, how to fix it?
* this is wrong, how to fix it?
- cur. challenge: limited prompt size
- reasoning power?
#Dagstuhl
- compiler testing: generate programs
- "like" static analyzers:
* what is wrong, how to fix it?
* this is wrong, how to fix it?
- cur. challenge: limited prompt size
- reasoning power?
#Dagstuhl
Q: Isn't it the *unusual* and the *unlikely* that makes us find bugs?
A: You can increase temperature. Make it hallucinate more.
A: You can increase temperature. Make it hallucinate more.
C: LLMs can't be trusted. Instead of bug finding, we should find use cases where we don't *need* to trust it. Maybe use it as a fuzzer guidance?
C: LLMs are good at dialogue. Maybe use it in an interactive manner?
• • •
Missing some Tweet in this thread? You can try to
force a refresh
