I’m not saying that your approach is wrong. But most LLM workflows are either brute forcing the solution, or seeking a local minima to be stuck in. It’s like doing thousands of experiments of objects falling to figure out gravity while there’s a physics textbooks nearby.
That said, I’m building a product - not a PPP driver - so the quicker I can fix the problem and move on, the better.
There’s no way I could fully read that RFC in an hour. And that’s before you even know what reading to focus your attention on, so you’re just being a worse LLM at that point.
In any case, LLMs are not magical forgetfulness machines.
You can use a calculator to avoid learning arithmetic but using a calculator doesn’t necessitate failing to learn arithmetic.
You can ask a question of a professor or fellow student, but failing to read the textbook to answer that question doesn’t necessitate failing to develop a mental model or incorporate the answer into an existing one.
You can ask an LLM a question and blindly use its answer but using an LLM doesn’t necessitate failing to learn.
However, even outside of using a LLM the temptation is always to keep the blinders on do a deep dive for a very specific bug and repeat as needed. It’s the local minima of effort and very slowly you do improve as those deep dives occasionally come up again, but what keeps it from being a global minimum is these systems aren’t suddenly going away. It’s not a friend’s expresso machine, it’s now sitting in your metaphorical kitchen.
As soon as you’re dealt with say a CSS bug the odds of seeing another in the future are dramatically higher. Thus optimizing for diminishing returns means spending a few hours learning the basics of any system or protocol you encounter is just a useful strategy. If you spend 1% of your time on a strategy that makes you 2% more efficient that’s a net win.
But that's not learning or even problem's solving. It's just a time saving trick. And one that's not reliable.
And the fact is that there's a lot of information about pretty much anything. But I see people trying to skip the foundation (not glamorous enough, maybe) and go straight for the complicated stuff. And LLMs are good for providing the illusion that it can be the right workflow.
Well said. You can only spend years digging into the intricacies a handful of systems in your lifetime, but there’s still real rewards from a few hours here and there.
I do agree with you that an LLM should not always start from scratch.
In a way it is like an animal which we have given the ultimate human instinct.
What has nature given us? Homo Erectus is 2 million years ago.
A weird world we live in.
What is context.
I’d argue that’s a more effective capture as to what I would remember anyway.
If wanted to learn more (in a general sense) I can take the manual away with me and study it, which I can do more effectively on its own terms, in a comfy chair with a beer. But right now I have a problem to solve.
IE LLM then RFC takes more time then RFC then solving the issue.
Because you should have read RFC 1331.
Even then your argument assumes that optimising for total time (to include your own learning time) is the goal, and not solving the business case as a priority (your actual problem). That assumption may not be the case when you have a patch to submit. What you solve at what time point is the general case, there’s no single optimum.
Having a less skilled worker is a tradeoff for getting one very specific task accomplished sooner, that might be worth it especially if you plan to quit soon but it’s hardly guaranteed.
Whereas it's been all morning and you're still reading the RFC, and it's the wrong RFC anway.
I know who i'd hire.
This time it worked, but I’ve been forced for fire people with this kind of attitude before.
> LLMs allowing optimal time use in certain case
I never said it was slower, I’m saying what’s the tradeoff. I’ve had this same basic conversation with multiple people, and after that failed the only real option is to remove them. Ex: If you don’t quite understand why what you wrote seemingly fixes a bug don’t commit it yet, seems to work isn’t a solution.
Could be I’m not explaining very well, but ehh fuck em.
I have really learned to mistrust and double check every single line those systems produce. Same for writing code. Everything they produce looks nice and reasonable on the surface but when you dig deaper it falls apart unless it's something very very basic.
I totally agree that LLMs are great at compressing information; I've set up the docs feature in Cursor to index several entire large documentation websites for major libraries and it's able to distill relevant information very quickly.
Sometimes it is good to start new chat or switch to Claude.
And it really helps to be very precise with wording of specification what you want to achieve. Or repeat it sometimes with some added request lines.
GIGO in reality :)
Yeah, they do come across as "overly eager junior devs", good comparison. :D
Personally I think it's a lot better via the API than ChatGPT. ChatGPT doesn't let you edit the "system prompt" which is really where you wanna put "how to" instructions, so it really follows them. Instructions put in the user message aren't followed as closely as when you use the system prompt, so probably why it still did something, if you were using ChatGPT.
I am giving up on providing code, and on checking is it working, because it is very time consuming. Tell me when it starts working. Good luck.
:)
At the end of the two weeks, I observed that: The LLM was much less likely to become distracted. Sometimes, I would dump whole forum threads or SO posts into it, when it said "this is not what we are seeing here, because of [earlier context or finding]. I eliminated all dead ends logically and informed it of this (yes, it can help with the reflection, but I had to make the decisions). In the end, I found the cause of my issues.
This somewhat confirms what some user here on HN said a few days ago. LLMs are good at compressing complex information into simple one, but not at expanding simple ideas into complex ones. As long as the output was larger than my input, I was happy with the results.
I could have done this without the LLM. However, it was helpful in that it stored facts from the outset that I had either forgotten or been unable to retrieve quickly in new contexts. It also made it easier to identify time patterns in large log files, which helped me debug my site-to-site connection. I also optimized many other settings along the way, resolving not only the most problematic issue. This meant, in addition to fixing my problem, I learned quite a bit. The 'state' was only occasionally incorrect about my current parameter settings, but this was always easy to correct. This confirms what others already saw: If you know where you are going and treat it as a tool, it is helpful. However, don't try to offload decisions or let it direct you in the wrong direction.
Overall, 350k Tokens used (about 300k words).