Model intelligence is no longer the constraint for automation

Post by fmbb » Sun, Aug 17, 2025, 6:45 PM UTC

exe34 wrote: post #118

fmbb wrote: post #74

> It’s because the bottleneck isn’t in intelligence, but in human tasks: specifying intent and context engineering. So the bottleneck is intelligence. Junior engineers are intelligent enough to understand when they don't understand. They interrogate the intent and context of the tasks they are given. This is intelligence. Solving math questions is not intelligence, computers have been better than humans at that for l…

> Junior engineers are intelligent enough to understand when they don't understand. They interrogate the intent and context of the tasks they are given Eh, I wouldn't apply that as if it's a general thing. yes, the really good ones do. many will equally plough through into the mud with albeit admirable determination.

Post by exe34 » Sun, Aug 17, 2025, 8:59 PM UTC

fmbb wrote: post #151

exe34 wrote: post #118

Earlier quoted context omitted.

> Junior engineers are intelligent enough to understand when they don't understand. They interrogate the intent and context of the tasks they are given Eh, I wouldn't apply that as if it's a general thing. yes, the really good ones do. many will equally plough through into the mud with albeit admirable determination.

yeah so the LLMs are like a stupid junior only they work for free and produce megabytes of stupid code per hour

Post by patrickhogan1 » Sun, Aug 17, 2025, 11:42 PM UTC

themanmaran wrote: post #140

patrickhogan1 wrote: post #48

Earlier quoted context omitted.

Do you have a concrete example of what you mean? For example, the article above was insightful. But the authors pointing to 1,000s of disparate workflows that could be solved with the right context, without actually providing 1 concrete example of how he accomplishes this makes the post weaker.

Sure, concrete example. We do conversational AI for banks, and spend a lot of time on the compliance side. Biggest thing is we don't want the LLM to ever give back an answer that could violate something like ECOA. So every message that gets generated by the first LLM is then passed to a second series of LLM requests + a distilled version of the legislation. ex: "Does this message imply likelihood of credit approval (…