@[email protected] to [email protected]English • 1 year agoChatGPT gets code questions wrong 52% of the timewww.theregister.comexternal-linkmessage-square9fedilinkarrow-up1159arrow-down15cross-posted to: [email protected]
arrow-up1154arrow-down1external-linkChatGPT gets code questions wrong 52% of the timewww.theregister.com@[email protected] to [email protected]English • 1 year agomessage-square9fedilinkcross-posted to: [email protected]
minus-square@[email protected]linkfedilink6•1 year ago52% In the first year is pretty cool, excited to see how it will evolve.
minus-squarecircuitfarmerlinkfedilink2•1 year agoProbably far enough that anyone with an actual interest will be out of a job.
minus-square@[email protected]linkfedilink2•1 year agoGPT4 with reflexion prompting gets 90% correct (for HumanEval coding benchmark). The paper this is based on is misleading at best.
52% In the first year is pretty cool, excited to see how it will evolve.
Probably far enough that anyone with an actual interest will be out of a job.
GPT4 with reflexion prompting gets 90% correct (for HumanEval coding benchmark). The paper this is based on is misleading at best.