I’ve used it for several improvements to our wysiwyg. I was able to refactor to a much more cohesive architecture that is making future work much easier/safer. We got a fzf like search algorithm for an autocomplete that includes marking which characters matched. It fixed some jank performance issues I was struggling to track down.
Fixed small several bugs last week without even open the editor. It wrote tests that confirmed the bugs, then fixed them. Then I manually confirmed as well.
It built a double entry event log. A single application event produces two logs, one for the person doing the action, one for the person being acted upon.
For a nasty problem we have, we had AI prototype 2 different solutions. Then we reveiewed them as a team. We threw those out but it was very helpful input into our decision making.
> I’ve used it for several improvements to our wysiwyg. I was able to refactor to a much more cohesive architecture that is making future work much easier/safer. We got a fzf like search algorithm for an autocomplete that includes marking which characters matched. It fixed some jank performance issues I was struggling to track down.
so, basically did some vague, almost incomprehensible stuff. seems par for the course.
How was any of that incomprehensible? They gave a list of some actual things they shipped. The hand wavy dismissal where you pretend they didn’t say anything just exposes your bias. You don’t want to hear a success story so you don’t.
Checking all the past "what are you working on?" threads just to realize that, somewhere in August 2024 stuff just exploded and the average thread goes reached ~1000 messages, from ~50 pre-August.
I shipped this shader based video compositor as part of a bigger project ive been working on since before LLMs but the compositor was 100% ai and it works fantastically. It's not a huge project but I and a number of my users use it. https://lowkeyviewer.com/studio/
I did ship a quite efficient quantum simulator as a toy out of other work (and a block truncation certificate as a side-product). https://github.com/cgiogkarakis/qut
I have been thinking about this for a while, because I personally need a career pivot but I was going to move into personalised training, and I think AI likely really messes with the viability of that.
If you characterise questions as bad faith so you don’t have to answer, sure.
Since this is my thread, and since I am an exasperated freelancer who has made most of his post-dot-com career from writing exactly the kind of quite small, simple, unambitious, often internal things for smaller customers that nobody would confuse with anything cool, who is trying to understand how AI is going to make his life any better when it’s so opaque, fast moving, poorly documented and full of unverifiable claims battling unverifiable claims, let me assure you that the following question is not being asked in bad faith:
I've shipped small, simple, unambitious internal things for our company that saved people lots of time, and I've shipped them in minutes rather than the a day or two they used to take.
I've just shipped a migration from our old auth service to the new one in a week, a migration that we've put off for three years because it would take the team months to finish.
Thank you for the details! These are precisely the kind of things I want to hear about because they are self-contained and I can judge against the kind of stuff I do.
I am quite interested in experimenting with it for migrations, because for example I have a set of sites written in older Nuxt and Vue and Buefy that need refreshing (and the frontend ported to that UI-agnostic Buefy replacement whose name escapes me at the moment but begins with “ou” I think). These migrations won’t happen any other way (small customers won’t pay for that) so I am open to whether tooling can reduce the cost I have to swallow. LLMs I have tested (including local models) seem to support the idea that this will be doable but I am a little out of the loop with the projects so I haven’t got back to this yet.
The hardware thing looks great; I am a sort of distracted maker and FreeCAD nerd but I often need a nudge to get started and I have found an LLM chat to help there a little bit (though it cannot answer some questions if I don’t have the specific vocabulary).
Writelucid is definitely cute.
I think you should not be put off talking about these things because whether people agree with you or not about whether they are important, they can at least measure against them.
You're welcome! LLMs definitely help with the migrations, there were definitely a few iterations because the surface area was massive, but overall it took the project from "will never be prioritised" to "I can work on it on and off when in boring meetings", which was a massive win.
I haven't found that LLMs help with CAD at all, but YMMV.
As for sharing here, the last time I shared something with "here's something I made with LLMs", the reply was "it shows", and that's just the latest instance. It just puts me off the whole thing.
Oh I definitely don't expect them to help with CAD and nor would I want them to — I really enjoy knowing FreeCAD.
It's more the microcontroller choice, broad components, all that.
The main areas I find LLMs struggle with research, I struggle with research too. I am a pretty solid researcher and I find it validating, in fact, to find that a more brute-force-trained thing is not better than me.
I see your point about the snarky reply; I must admit I have probably in the more distant past been somewhat snarky but I stopped commenting like that whenever I spot myself doing it because I know it is dispiriting.
(The other reply, re: early and late stages, is the kind of substantive question that lingers in my mind).
Anyway I just want to reiterate my thanks: I am sort of cynical about this, in that I believe the technologies may have their uses, but I have no time for the cult and the hype train, so it is nice to see anyone talking about actual things.
> I can work on it on and off when in boring meetings
That’s not a sign of a healthy org. If you’re in a meeting it’s disrespectful not to be present. If you think a meeting is not useful you should reject it.
I concur. I really want to see this from the "small stuff" upwards, which is probably why my own interest starts with local models and grows outwards, but all of these things are worth hearing.
I don't use it to ship whole products. I have it do some tasks.
I have it code dsp techniques in journal articles I hand it. I have it create the unit tests, pipelines documentation. Then I manually verify the test cases aren't wrong and run the tests. If they pass it does what I wanted and I start looking at the code quality. It varies from being better than I could have done it to being objectively bad. I fix it if it needs fixing, then I'm done.
I have also pointed it at issues in our backlog and it usually finds the subtle logic errors underlying the behavior in the issue.
I haven't started and entire product from zero and shipped it. Mostly because I haven't started a new product since it was capable of that. But also because it has a scale beyond which I don't find it as useful. I have used it for an entire repo, but in the crates.io or npm scale of repo, not boost scale.
I work at a 6 year old startup. Essentially every feature and bug fix we’ve shipped in the last year has had LLMs involved. Every project plan involved AI, either for writing or for codebase research. For code review we get AI to do the first pass.
Why assume bad faith? I've witnessed a barrage of "proof of concepts" at my dayjob by folks who have zero intention of ever hooking up their dashboard to our actual messy data. Shipping is still a major barrier. Is your experience meaningfully different?
My definition would be "users waiting for it who received it"; that's the one that fits the broadest real world definition of the word. Not everything is an organisation, not everyone is paying.
If the only user is the author, then I don’t see a meaningful distinction between shipped and not shipped. It’s like a blacksmith who said they invented a new tool with great value but they built it themselves and no one else is willing to use it because it’s so customized to their workflow.
Edit: I’ll add a caveat that I’d agree it was shipped if it’s making the author money even if they are the only user, but otherwise it all smells like dotcom era Pets.com level of selling a dollar for 99 cents and claiming it’s the future.
Many very well made software written without any AI was never "shipped" because there were no people who wanted to pay for it, many very poorly made software was shipped because demand and marketing did the job.
So evaluating software by "shipped or not" is just useless.
What a weird thing to downvote without comment. You doubt this? I am literally using AI right now to update software that generates tens of thousands of dollars of revenue annually.
My team redid a bunch of our ETL. I personally built a programming language that you can download and use, and I’m about to release an iOS app(in a few weeks).
Which is basically a fancy calendar and team management system for my Valorant Premier team haha
It’s on my GitHub as operators-premier-manager but note it is not great: it serves its purpose which is to wrangle my team to show up for practice and scrims
I'm hesitant to respond, because I haven't shipped yet and I haven't shown any evidence. But I am close enough to completion that I am certain Claude's work will be sufficient to ship.
From an implementation perspective, it is about 80% complete, where by "complete", I mean "adequately polished such that I could ship it." (I'm not interested in providing evidence of my claim at this time, and you are welcome to not believe me.) Most of the remaining 20% are optional game modes I could choose to cut (and may, for gameplay reasons).
I do not contend that the code is excellent. But to whatever extent the code is "slop", that has not meaningfully inhibited the ongoing development or caused noticeable issues with the player experience.
The game is not especially ambitious, but it's something I would have been unable to create without genAI. The version of me that could have made it without genAI would have taken > 10x as long to get as far as I've gotten.
That's fair critique, the README itself is indeed slop explicitly written by bots for bots. What it actually does and how it works is actually pretty neat if you care to look.
'Cause I don't have any quality user-facing documentation yet; that README is for bots. None of the interfaces have had a chance to settle, so any time spent accurately and humanely documenting what the project is capable of right now is an investment I cannot afford. I figured most people would just give it over to their favorite LLM with whatever instructions they prefer for translation because that's what I would've done...
I don’t mean to pick on you in particular here, but this approach has been bothering me a lot lately, and it seems like it’s super common.
I get that it’s an early prototype and not all the design choices are made yet, but I struggle with “I can’t afford human-readable documentation yet”. Isn’t human readable documentation important for efficiently planning and deciding what you want to build? I feel like I can’t afford not to have human readable docs and plans while the project is taking shape
Related, if a user can prompt an agent to translate to a human-readable summary, wouldn’t it be better to just do this in place? Sure, models can deal with noisy LLM outputs but shouldn’t a document that’s easier for humans also be easier for bots?
What does "that README is for bots" mean? Are you implying it is some kind of special language written by and correctly understood by bots/LLMs, but otherwise semantically coherent?
Wait so someone asked for something you made with AI that wasn't slop, and then you linked to something you knew was slop, and you said "I think this counts as something that isn't mere slop" and then when called out on it you admit you knew it was slop the whole time?
This is a frequent pattern among AI users. What causes it?
Some of us aren't just slopping it up like @theo and all the other AI influencers are, as I developed nearly every single line of this by hand over the span of the past decade. Agents recently became capable of factchecking it and helped find bugs that my other unit testing never caught. Software engineering has never been more alive!
This is a snippet I wrote years ago to help me study different formulations of the equation ((1 + √5) / 2). There was this thing I could "see" in there that would allow me index into these sequences, and whole families of others, in O(1) time. The problem is that I still don't know enough maths to derive the exact object that I want from the nonsense that I have.
This is the reformulation of that snippet into a proper object, distilled using Fable and Sol. Unlike BinaryIntegerFunctions, I didn't write a line of this and I'm quite happy with that. It's been a slog for so long... being able to let these agents toil away at all the off-by-one type noise is just nice. I get to focus on an actual product for once instead of manufacturing every single nut and bolt myself.
I am just confused on how you know that all of what has been generated is valid. When you write the code generator yourself, you have that level of confidence.
It's mathematically provable in most cases because the engine is deterministic from the ground up and I refused to ever compromise on that one detail. For example, nearly all of the VM and maths code functions have been validated for ALL possible 32-bit inputs and extensively fuzz tested in the 64-bit range. Even the more complicated sections of the code like the emulators have batteries of third party tests that ensure a certain level of compliance. The fact that you can play commerical ROMs to completion, including esoteric titles that require third party peripheral/MBC code, is quite solid proof too!
A form of recursion is also doing a lot of heavy lifting because the emulators are their own separate deterministic engines that are dynamically plumbed into the primary loop. This not only allows us to embed diegetic devices (as in, you can literally pick up a glowing brick in the world, hold it to your face, and play it), but also validates that the primary loop is coded accurately because the outer loop runs at X Hz while humble bricks must run at ~59.7275 Hz. Pacing inaccuracies in the main loop cause us to fail the brick suites that we test against. This concept of having features reinforce one another is applied as often as possible.
The obsession with determinism goes so far that both the DirectX and Vulkan backends are validated against each other for pixel level differences. If they differ more than the expected maximum then code is refactored until the drift is back within acceptable range.
It's not a full game yet, but the substrate on which I am building one. It implements a completely deterministic SDF VM rendering engine that allows edits in real-time at acceptable performance levels. The engine is essentially folded in on itself as the editor is the game; assuming that an editor mode was actually defined in the world document. It's a lot...
Fixed small several bugs last week without even open the editor. It wrote tests that confirmed the bugs, then fixed them. Then I manually confirmed as well.
It built a double entry event log. A single application event produces two logs, one for the person doing the action, one for the person being acted upon.
For a nasty problem we have, we had AI prototype 2 different solutions. Then we reveiewed them as a team. We threw those out but it was very helpful input into our decision making.