cm0002@suppo.fi to Programmer Humor@programming.dev · 3 天前They're just like us!suppo.fiimagemessage-square57fedilinkarrow-up1829arrow-down110
arrow-up1819arrow-down1imageThey're just like us!suppo.ficm0002@suppo.fi to Programmer Humor@programming.dev · 3 天前message-square57fedilink
minus-squareFishFace@piefed.sociallinkfedilinkEnglisharrow-up64arrow-down2·2 天前Weird that anyone capable of understanding “test suite” is incapable of understanding that LLMs don’t make progress when not generating tokens
minus-squareRustyNova@lemmy.worldlinkfedilinkarrow-up22·2 天前TBF it could be hidden behind a fancy spinner, making you incapable of seeing what the AI is generating, like devin. For exemple: https://www.youtube.com/watch?v=927W6zzvV-c
minus-squareSleeplessCityLights@programming.devlinkfedilinkarrow-up9·2 天前Some models hide their reasoning all together, but at the end spit out a summary of their reasoning. Its useless.
Weird that anyone capable of understanding “test suite” is incapable of understanding that LLMs don’t make progress when not generating tokens
TBF it could be hidden behind a fancy spinner, making you incapable of seeing what the AI is generating, like devin.
For exemple: https://www.youtube.com/watch?v=927W6zzvV-c
Some models hide their reasoning all together, but at the end spit out a summary of their reasoning. Its useless.