RSS Bot@lemmy.bestiver.seBM to Lobste.rs@lemmy.bestiver.seEnglish · 6 months agoTreat Agent Output Like Compiler Outputskiplabs.ioexternal-linkmessage-square2linkfedilinkarrow-up13arrow-down10file-text
arrow-up13arrow-down1external-linkTreat Agent Output Like Compiler Outputskiplabs.ioRSS Bot@lemmy.bestiver.seBM to Lobste.rs@lemmy.bestiver.seEnglish · 6 months agomessage-square2linkfedilinkfile-text
minus-squaredustycups@aussie.zonelinkfedilinkEnglisharrow-up1·6 months agoI’m no expert in this field, but surely a compilers output is deterministic. There are plenty of examples of LLM generated code doing suicidally reckless things. Testing it by setting it loose on production sounds… risky. What kind of automated tests do you guys use & how would they go if you did zero code review?
I’m no expert in this field, but surely a compilers output is deterministic.
There are plenty of examples of LLM generated code doing suicidally reckless things. Testing it by setting it loose on production sounds… risky.
What kind of automated tests do you guys use & how would they go if you did zero code review?