Hacker Newsnew | past | comments | ask | show | jobs | submit | toddmorrow's commentslogin

AGI = Reasoning

I can reason. Sometimes. It's very hard. My buddy Deepseek can't. This is like the scene in Blue's Clues where the answer is obvious and the kids are yelling but blue can't see it. Facts abound, but not conclusions based on those facts

There's a reachable intermediate step on the way before reasoning, and that's "keeping the plot". Not losing the line of thought.


so open claw will be neither open nor claw

this is like the doomsday clock

84% is meaningless if these things can't reason

getting closer and closer to 100%, but still can't function


> if these things can't reason

I see people talk about "reasoning". How do you define reasoning such that it is clear humans can do it and AI (currently) cannot?


gitcoin lol

right, the ethereum gets spent whether the transaction is cancelled or not. and that's an issue

there are many many examples where paying a nominal fee seems like it would get rid of the clowns. and it would. almost any place where the public can "post". but the challenge is to not inadvertently throw out the good ones.

once notable policy SQL Server enterprise support used to have was you must be available 24/7 if you submit a critical issue. Microsoft was demanding as much of their time as our time.

not sure how that could be rolled out to repos but it worked


this is just marketing press from big AI

LLMs are like a jack hammer. very good if you hold it and point it. you cannot let go of it for more than half a second. it can hammer but it cannot guide itself.

LLMs have irritated me with bad solutions but they've never hurt my feelings. I can't say that about a single person I know. They're better people than people lol

Facebook is what killed that. Not AI

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: