cyrano@lemmy.dbzer0.com to Lemmy Shitpost@lemmy.world · 12 天前AGI achieved 🤖lemmy.dbzer0.comimagemessage-square252fedilinkarrow-up1909arrow-down115
arrow-up1894arrow-down1imageAGI achieved 🤖lemmy.dbzer0.comcyrano@lemmy.dbzer0.com to Lemmy Shitpost@lemmy.world · 12 天前message-square252fedilink
minus-squarecyrano@lemmy.dbzer0.comOPlinkfedilinkarrow-up16·edit-212 天前Try it with o3 maybe it needs time to think 😝
minus-squareEager Eagle@lemmy.worldlinkfedilinkEnglisharrow-up4·edit-212 天前which model is it? I had a similar answer with 3.5, but 4o replies correctly
minus-squareThirdConsul@lemmy.mllinkfedilinkarrow-up1·edit-212 天前IIRC if you take s look at 4o leaked instruction (prompt that is “injected” at the begining of the chat), that model is clearly ordered HOW to solve this kind of problem lol
minus-squareThirdConsul@lemmy.mllinkfedilinkarrow-up4·12 天前Sorry, that was Claude 3.7, not ChatGPT 4o https://github.com/elder-plinius/CL4R1T4S/blob/d9a004b5a29395675c5a548acfc386459f71cd14/ANTHROPIC/Claude_Sonnet_3.7_New.txt#L92
minus-squareEager Eagle@lemmy.worldlinkfedilinkEnglisharrow-up3·12 天前ah, that’s reasonable though, considering LLMs don’t really “see” characters, it’s kind of impressive this works sometimes
Try it with o3 maybe it needs time to think 😝
which model is it? I had a similar answer with 3.5, but 4o replies correctly
IIRC if you take s look at 4o leaked instruction (prompt that is “injected” at the begining of the chat), that model is clearly ordered HOW to solve this kind of problem lol
are you sure?
Sorry, that was Claude 3.7, not ChatGPT 4o
https://github.com/elder-plinius/CL4R1T4S/blob/d9a004b5a29395675c5a548acfc386459f71cd14/ANTHROPIC/Claude_Sonnet_3.7_New.txt#L92
ah, that’s reasonable though, considering LLMs don’t really “see” characters, it’s kind of impressive this works sometimes