ijeff@lemdro.id to Technology@beehaw.orgEnglish · 1 year agoIntroducing Code Llama, a state-of-the-art large language model for codingai.meta.comexternal-linkmessage-square2fedilinkarrow-up144arrow-down10file-textcross-posted to: eric_posts_urls@discuss.onlineaistuff@lemdro.idprogramming@programming.devtechnews@radiation.partyhackernews@derp.foo
arrow-up144arrow-down1external-linkIntroducing Code Llama, a state-of-the-art large language model for codingai.meta.comijeff@lemdro.id to Technology@beehaw.orgEnglish · 1 year agomessage-square2fedilinkfile-textcross-posted to: eric_posts_urls@discuss.onlineaistuff@lemdro.idprogramming@programming.devtechnews@radiation.partyhackernews@derp.foo
minus-squared3Xt3r@beehaw.orglinkfedilinkarrow-up12·edit-21 year agoLooks interesting, but doesn’t seem better than GPT-4. GPT-4 scored 67% on the Human Eval test, whereas Code Llama scored only a 53.7%, which isn’t a trivial difference. Bit disingenuous of Meta to claim it to be “on par” with ChatGPT.
minus-squareijeff@lemdro.idOPlinkfedilinkEnglisharrow-up6·1 year agoThey seem to qualify a bit below that they mean GPT-3.5-Turbo, which does often get referred to as ChatGPT (in contrast to GPT-4).
Looks interesting, but doesn’t seem better than GPT-4. GPT-4 scored 67% on the Human Eval test, whereas Code Llama scored only a 53.7%, which isn’t a trivial difference. Bit disingenuous of Meta to claim it to be “on par” with ChatGPT.
They seem to qualify a bit below that they mean GPT-3.5-Turbo, which does often get referred to as ChatGPT (in contrast to GPT-4).