181–190 of 265 posts
I have a feeling that the same idea absolutely does apply to code . Writing code is much closer to writing prose than it may seem. And the act of writing code also makes you think as you write. Even if you're writing boilerplate. Because how else would you uncover subtle opportunities to reduce the boilerplate and introduce new, better abstractions?
Earlier quoted context omitted.
Coordinating with people is hard and only gets harder as you live. And actually, finding someone that is earnestly receptive to hearing you pitch your half-baked startup ideas (just an example) and is in some capacity qualified to be at all helpful, is uhhh, not easy.
Really? Sometimes I think I'm not very social, then I read something like this. Don't you have any friends? Colleagues? Maybe that's the problem you need to solve rather than sitting in a room burning energy for endless token streams with LLMs that anyone has access to?
Both LLM based rubber-ducking and human discussions seem like a win win. I see no reason to jump to labeling unhealthy social connections just for pairing with LLMs.
I've long considered writing to be the "last step in thinking". I can't tell you how many times an idea, that was crystal clear in my mind, fell apart the moment I started writing and I realize there were major contradictions I needed to resolve. Likewise I also have numerous times where writing about something loosely and casually revealed to me something that fundamentally changed how I viewed a topic and really co…
This was definitely not written by AI. Granted their many drawbacks, present-day AI engines avoid this classic grammatical error.
However! Future, more advanced AI engines will slather their prose with this kind of error, to conceal its origins.
Earlier quoted context omitted.
Sometimes I don't want creativity though, I'm just not familiar enough with the solution space and I use the LLM as a sort of gradient descent simulator to the right solution to my problem (the LLM which itself used gradient descent when trained, meta, I know). I am not looking for wholly new solutions, just one that fits the problem the best, just as one could Google that information but LLMs save even that searchin…
> I'm just not familiar enough with the solution space Neither is the LLM
I've read the thread and in my mind you're missing that LLMs increase the surface area of visibility of a thing. It's a probe. It adds known unknowns to your train of thought. It doesn't need to be "creative" about it. It doesn't need to be complete or even "right". You can validate the unknown unknown since it is now known. It doesn't need to have a measured opinion (even though it acts as it does), it's really just topography expansion. We're getting in the weeds of creativity and idea synthesis, but if something is net-new to you right now in your topography map, what's so bad about attributing relative synthesis to the AI?
Earlier quoted context omitted.
> I'm just not familiar enough with the solution space Neither is the LLM
No, this is the kind of thing LLMs are very good at. Knowing the specifics and details and minutiae about technologies, programming languages, etc.
Earlier quoted context omitted.
If you drop the premise of writing, drop the premise that you need something well written. Just give me the same information you would have given the LLM.
Do you really want five minutes of audio of me rambling, then some instructions for how to split it up and organise it? Plenty of people make LLMs make text longer, but writing a short accurate text with the essential points is much harder.
Earlier quoted context omitted.
If you drop the premise of writing, drop the premise that you need something well written. Just give me the same information you would have given the LLM.
But a non well-written prompt is not a good prompt. What are you really going to do with a shit prompt? It's meta: we need better writers all the way down.
Everything coming out of LLM on any prompt is either someone else's decisions or same thing reworded in a different way.
I've long considered writing to be the "last step in thinking". I can't tell you how many times an idea, that was crystal clear in my mind, fell apart the moment I started writing and I realize there were major contradictions I needed to resolve. Likewise I also have numerous times where writing about something loosely and casually revealed to me something that fundamentally changed how I viewed a topic and really co…
For your context, I'm an AI hater, so understand my assumptions as such. > The obvious best solution is to have your agent write release notes for your agent in the future to have context. No more tedious writing or reading, but also no missing context. Why is more AI the "obvious" best solution here? If nobody wants to read your release notes, then why write them? And if they're going to slim them down with their AI…
If you are coding with the help of LLMs, then release notes are your human-crafted prompt.
Basically, the intent is given as a decision somewhere, and that is human driven.
Earlier quoted context omitted.
For your context, I'm an AI hater, so understand my assumptions as such. > The obvious best solution is to have your agent write release notes for your agent in the future to have context. No more tedious writing or reading, but also no missing context. Why is more AI the "obvious" best solution here? If nobody wants to read your release notes, then why write them? And if they're going to slim them down with their AI…
This is kind of a fundamental issue with release notes. They are broadcasting lots of information, and only a small amount of information is relevant to any particular user (at least in my experience). If I had a technically capable human assistant, I would have them filter through release notes from a vendor and only give me the relevant information for APIs I use. Having them take care of the boring, menial task so…
An LLM could do this by looking over the full codebase and release notes and do a shorter summary, bit probably at the cost of many tokens today.
Earlier quoted context omitted.
For your context, I'm an AI hater, so understand my assumptions as such. > The obvious best solution is to have your agent write release notes for your agent in the future to have context. No more tedious writing or reading, but also no missing context. Why is more AI the "obvious" best solution here? If nobody wants to read your release notes, then why write them? And if they're going to slim them down with their AI…
What better solution do you have in mind? This scenario is AI being used as a tool to eliminate toil. It’s not replacing human creativity, or anything like that. If you have a problem with that, then you should also have a problem with computers in general. But maybe you do have a problem with computers - after all, they regularly eliminate jobs, for example. In that case, AI is only special in its potentially greate…
What OP did was "we lacked communication, then created ineffective process that achieved nothing, so we automated the ineffective process and pay third party for doing it".
If you pay tokens for release notes that nobody reads, they you may just ... not pay tokens.