41–50 of 71 posts
> a set of rules, roles, and workflows that make its output predictable and valuable. Let me stop you right there. Are you seriously talking about predictable when talking about a non-deterministic black box over which you have no control?
Would you say a top tier human developer produces predictable output? I would, in the sense that it will be well designed and implemented code that meets the requirements. Can we guess every variable name and logic choice? Probably not.
First you'd have to prove that LLMs can be equated to a "top tier human developer"
> I would, in the sense that it will be well designed and implemented code that meets the requirements.
Indeed. Something LLMs can or cannot do with all the predictability of a toss coin.
> a set of rules, roles, and workflows that make its output predictable and valuable. Let me stop you right there. Are you seriously talking about predictable when talking about a non-deterministic black box over which you have no control?
Would you still call that predictable? Of course you would, as long as they meet your requirements. Put it another way, anything is unpredictable depending on your level of scrutiny. AI is likely less predictable than human, doesn’t mean it isn’t helpful. You are free to dismiss it of course.
Earlier quoted context omitted.
That is exactly my point.
Then no one understands your point
I'll put it concisely:
Trying to build predictable result upon unpredictable, not fully understood mechanisms is an extremely common practice in every single field.
But anyway you think LLM is just coin toss so I won't engage with this sub-thread anymore.
Earlier quoted context omitted.
Then no one understands your point
Maybe you can try to read other comments below your original comment, as they mostly share the same point and I don't bother to repeat what everyone else has said. I'll put it concisely: Trying to build predictable result upon unpredictable, not fully understood mechanisms is an extremely common practice in every single field. But anyway you think LLM is just coin toss so I won't engage with this sub-thread anymore.
Nothing in the current AI world is as predictable as, say, the medicine you can buy or you get prescribed. None of the shamanic "just one more prompt bro" rituals have the predicting power of physics laws. Etc.
You could reflect on that.
> But anyway you think LLM is just coin toss
A person telling me to "try to read comments" couldn't read and understand my comment.
I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what?
I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training.
Now we try to poison the context with lots of (for my actual task at hand) useless information so that the model can conform to my superficial song-and-dance process? This seems backwards.
I would argue that we need less context poisoning with useless information. Give the model the most precise information for the actual work to be done and iterate upon that. The song and dance process should happen outside of the context constrained agent.
I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…
I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…
I do agree that context poisoning is a real thing to watch out for. Coincidentally, I’d noticed MCP endpoint definitions had started taking a substantial block of context for me (~20k tokens), and that’s now something I consider when adopting any MCP.
Earlier quoted context omitted.
Same with taskmaster, also not there.
I never found taskmaster that useful, something about how it forced you to work didn’t click with me…