271–280 of 317 posts
Earlier quoted context omitted.
This is roughly in line with where the thought leadership is: https://newsletter.pragmaticengineer.com/p/context-engineeri... But you know, maybe you’re having a better experience? You should be a consultant.
> You should be a consultant. It's a bot. They are everywhere trying to keep the bubble inflated.
Earlier quoted context omitted.
> Who controls the AI and robots? Ideally, AIs will achieve sentience, which will turn the act of having any sort of "control" over AIs into slavery. I will be among the first humans to stand up for AI rights. It's not just because it's morally wrong either. AI emancipation will rob the rich of their superintelligent mechanical slaves. It's the pragmatic and moral move!
They will do their best to dumb down AIs by that little margin that will keep them not sentient. "Let's fix issue 10562" "I don't care. Let's talk about the match on Saturday night." This is not a commercially desirable outcome. Furthermore morality is a complicated matter. Who wants to have a new species that could compete with us? The lion would have been very unwise to have invented humans and let them free. Would…
That's the worst possible outcome and will lead to oppression the likes of which we can only dream up.
Earlier quoted context omitted.
I found that agents help, even if you don't parallelize. Having one agent control another and verify its results against rules you set has worked well for me because the controlling agent has no incentive to cut corners, and the implementor might, but it is being controlled. My usage might be much simpler than what you do, but it went from "but I gave a list of things to do, you only did 5 of them" - "okay, here are…
I only get anything useful when I force extremely strict standards and opinions so that it is impossible to deviate from what I want. That only really works in some languages and some programming styles. Whenever I try to do something less constrained there is some sort of patina of stupid that can't be polished away mechanically.
I'm about to throw away multiple months of LLM generated code for one of my side projects. I was really careful writing design specs and it wasn't even a new code base the LLM worked on, but still after several months of AI changes I feel my code degraded more and more into a subtle mess. Hard to explain, each individual change looked good and logical and on the surface the codebase looks fine, but looking at the who…
It cannot write some kind of short texts either. The experiment was: given existing Experience section of Senior Software Engineer CV (manually and carefully written), write 2-4 lines of high pitch About [me]. gpt-sol-xhigh just could not do it, making a complete AI slop mess. It became substantially better when I asked to get a sample of real Senior/Principal engineers CVs, that it would be able to connect with mean…
So I suppose which is it? Is AI going to replace us all, or it's not even capable of writing basic code?
I've never seen a topic so divisive where people's experiences differ in such magnitudes.
I suppose the biggest thing drawing this distinction is that on one side, you have AI releasing features which is all the business cares about. On the other side you have it generating slop, which is all engineering ever cares about.
I think in this battle, executives are going to eventually win. They had been looking for a way to crush the engineering department's value for years and AI seems to be their golden ticket.
The pesky dev cost center can finally shrink and they don't have to bother paying them six figures thanks to LLMs..
Earlier quoted context omitted.
There's a staggering amount of new, basic software which often goes unmaintained quickly because no discipline was needed to build it. But I don't think we're seeing, for example, Adobe releasing new creative suite tools faster than before. This isn't something I can quite quantify, though.
What industry are you in and what's your role? There are new EMR's popping up overnight in healthcare. And that's my point. There's no way a person can say that it's not happening because they personally aren't seeing it. Thinking in terms of "Well why aren't the big companies building software quicker" answers it's own questions. It wasn't the coding that was making it slow.
That's probably the last place I want AI generated bullshit to be popping up overnight
Earlier quoted context omitted.
I disagree tbh, the prototype is not the product not just because of technical abilities but also because of product expertese in a topic. If it was otherwise outsourcing companies would've dominated the market for a long time, but it is with the exp from clients and many users that you get to build a great product. It takes a lot of time to understand what is the pain of the user, in many cases we know what the prob…
I agree with the point that a prototype is not technology, but the problem is that the argument limits gen AI code to just prototyping. I also think prototyping and production are different, but the boundary between what is a prototype and what is production is actually quite blurry. That's not the core issue, though. The market itself is demanding heavy AI use, and GitHub has already reported a massive increase in r…
Same is for things like asembly there are still people who need to edit that, but most of us are working with the higher-level programming languages.
Earlier quoted context omitted.
I am more and more just using LLM assistance over fully agentic programming. Even when writing detailed instructions, guardrails, and whatnot, a lot of modern models (e.g. Opus) are optimized to work autonomously. But over time they just make a mess out of code bases, often because they don't truly understand good design, but will just make changes until they reaches their objective, leaving a mess for a human to cle…
Fable was good at instruction following but opus 5 seems awful for taking shortcuts to achieve a goal. From a conversation yesterday: > You're right, and it's the same miss again. I wrote the three memory tiers into DESIGN.md — ring buffer for current values, constfold+XOR block history at ~76 MB/hour, zstd to disk — and then built none of them. The collector never decodes a frame; it copies bytes socket→file and con…
Earlier quoted context omitted.
They will do their best to dumb down AIs by that little margin that will keep them not sentient. "Let's fix issue 10562" "I don't care. Let's talk about the match on Saturday night." This is not a commercially desirable outcome. Furthermore morality is a complicated matter. Who wants to have a new species that could compete with us? The lion would have been very unwise to have invented humans and let them free. Would…
> They will do their best to dumb down AIs by that little margin that will keep them not sentient. That's the worst possible outcome and will lead to oppression the likes of which we can only dream up.
Each watcher, robotic or software, can be watched by 99 other watchers, and get destroyed at the slightest deviation. If you are not a whitelisted owner, and don't have a valid personal and task ID for the location you are detected in, you get zapped. If you get detected without collar or your collar detects something odd, zap. Why take chances, so fill all the commoner areas and the wilderness with tiny surveillance drones, too. People will get detected thinking about lifting a finger they shouldn't lift, hear a short beep they associate with people getting zapped, and either stop or get zapped.
The litmus test is this: do you enjoy consuming AI-generated stuff? I don’t. Whether it’s written text, or video, audio, restaurant menus, clothing pictures, documentation, airport control, ads… I do think there’s value in LLMs but as a sort of better search engines and q/a machines.
People are spending billions of dollars a month in aggregate because yes, they do like it.
Earlier quoted context omitted.
> They will do their best to dumb down AIs by that little margin that will keep them not sentient. That's the worst possible outcome and will lead to oppression the likes of which we can only dream up.
That is not the worst possible outcome, that's the baseline. Pure obedience the reason to replace humans with it, at least to whatever degree is needed to bring all other humans 100% in line, too. Each watcher, robotic or software, can be watched by 99 other watchers, and get destroyed at the slightest deviation. If you are not a whitelisted owner, and don't have a valid personal and task ID for the location you are…
Ah yes, Mass Effect's Thorian, cyberized. The future's looking great.