HNHacker News
TopNewBestAskShowJobs

lilbigdoot

175 karma · joined June 14, 2026

submissionscomments
lilbigdoot··on Managing AI Coding Costs at Scale
Meanwhile I'm so proud that I'm keeping my hobby project under 10k lines and spend time trying to delete code for my own sanity
lilbigdoot··on Managing AI Coding Costs at Scale
Personal anecdote: I spent a few days hacking on my compiler to remove 1k lines of code (about 15% of total code) while preserving behavior

I was only able to do that after I had solved multiple related problems in different places and started introducing subtle bugs by accident / had difficulty detecting all edge cases

I've noticed whenever I use LLMs they introduce the same kind of thing but at much smaller scales than I would. They often suggest solving the wrong problem when I prompt them to diagnose specific bugs too. Usually opting for a shortcut that introduces its own issues and ironically calling the proper direction "too complex" when it's really not.

lilbigdoot··on Eight Myths on Software Engineering and GenAI
Anecdotally I find them helpful for design and I don't find them nearly as helpful for coding (strange, given others experiences reported online)

I am working on a compiler for an OCaml inspired language (I am on a sabbatical) and used them a lot in the early phases to check my ideas and search for prior work. I use them less now (mostly debugging at this point), but have made use of LLMs to write some pieces like source map generation, a couple of small and well known algorithms that were new to me, and an analyzer to dump a schema from a typescript module. Other times I've tried to use it for other things, I have ended up regretting it because of subtle bugs

I don't think it made the design phase any shorter but it definitely helped save me energy in researching and made that period feel less like a fever dream. Design phases can be draining for me so that was welcome

lilbigdoot··on LLMs reward expertise
This is the only way I've been able to get LLMs to produce code I will actually use. Manually selecting the context for them and asking for a specific piece or similar

I started using harnesses because they are good for when something breaks and it's not trivial to investigate so I'll have the agent tell me what's happening, then using that to produce my own change

lilbigdoot··on Apple says more ex-employees may have taken confidential data to OpenAI
Bullshit lol
lilbigdoot··on Don't be a meat proxy
Reading this is nightmare fuel right before I go to bed omg
lilbigdoot··on SwiftUI After 7 Years
I never really tried out Cocoa. What did you like about it?
lilbigdoot··on Show HN: Fuse – statically typed functional programming language
Scala and a few others use `[]` (the compiler itself is written in Scala)
lilbigdoot··on Show HN: Fuse – statically typed functional programming language
Just curious, what made you choose GRIN? I haven't heard of it but it looks neat!
lilbigdoot··on Go 1.27 Interactive Tour
This level of generics actually has me interested a bit in Go now.
lilbigdoot··on Golang proposal: container/: generic collection types
Yes, .NET had the benefit of coming second and using F#, which was originally essentially OCaml 4 on .NET, as it's testing grounds. Same for Async

I am considering .NET for one of my compilers backends because of the reified generics. .NET can even pass around an object with generic methods that get specialized via JIT at runtime each time it sees a new data type (with reference types sharing implementations). Which also ties back to having true value types

It's a shame it took so long for .NET core to come around because even today the platform carries a reputation for being windows first which hasn't really been true for many years now

lilbigdoot··on Google fixed more Chrome bugs in June than over the past two years, thanks to AI
I don't know why people keep acting like any kind of LLM skepticism or criticism is based on bristled fur or something.

I am very skeptical of these workflows, but I also use LLMs regularly. I specifically use them because they are better than me at sifting through massive amounts of complex information. They are also quite, uh, sketchy, for things that are significantly easier. A total mixed bag in my experience that ultimately is useful, and I will continue to use

lilbigdoot··on Google fixed more Chrome bugs in June than over the past two years, thanks to AI
I had a model yesterday suggest that I intern all float literals in my compiler to save on memory lmao
lilbigdoot··on Google fixed more Chrome bugs in June than over the past two years, thanks to AI
Exactly. I'm a huge FP fan. When someone doesn't like FP I don't lecture them on how they're holding it wrong. I usually assume that, unsurprisingly, the tool doesn't suit every problem or there may be a design issue in the tool they ran into
lilbigdoot··on Google fixed more Chrome bugs in June than over the past two years, thanks to AI
No one in this chain said it sucks. Any sort of criticism towards LLM workflows is constantly met with these kinds of absurd statements. I've never seen any other tool with this kind of mentality from proponents
lilbigdoot··on Escape IntelliJ: Scala and Kotlin LSPs on Emacs Eglot
I had this thought yesterday where I wondered if there was a way to run an Android app in the browser (definitely non trivial, but something I would expect to exist in some form) and nothing. If LLMs are as good as people say they are, I should be seeing plenty of useful projects like that popping up but.... I just see harnesses and other random things
lilbigdoot··on Claude Is Not a Compiler
I've come to consider memory management the third
lilbigdoot··on Claude Is Not a Compiler
I think this is a great abstraction of the process I've never considered in those terms and I like it. It explains a bit of how software development differs from some other building processes where the desired outcome is being discovered as you figure out how to make something that produces that outcome
lilbigdoot··on Claude Is Not a Compiler
I was about to say a lot of algorithms or invariant bugs for me are slight mistakes at an edge of something
lilbigdoot··on Why do AI company logos look like buttholes? (2025)
That actually made me cackle ty
lilbigdoot··on What AI did to stackoverflow in a graph
I stopped posting there around then. Multiple times in a row I asked a question, got it closed as a duplicate/pointed to another thread/met with "why are you even trying to do that" despite being clear about my problem. It was obvious the people answering/closing the question skimmed it and I already gave a ton of context. It just stopped being useful
lilbigdoot··on The state of open source AI
I've tried GLM a few times but each time it ends up getting stuck in a loop and burning tons of tokens before I eventually kill it and restart. Has anyone had the same issue / know how to avoid it? I've been using Qwen 3.6 instead
lilbigdoot··on The state of open source AI
They also have huge influence over our military and laws. I immediately thought of the banana wars
lilbigdoot··on Solod: Go can be a better C
I've written multiple transpilers and their comment is how I do it. Safely mapping identifiers is one of those many edge cases you discover as you go along
lilbigdoot··on How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
A sine is only a part of most kicks
lilbigdoot··on Cannabis users face substantially higher risk of heart attack (2025)
Agreed. Blending in CBD and other cannabinoids is way more effective than relying on strains. Basically everything out there is extremely high in THC and nothing else. Mixing in high CBD flower reduces anxiety a lot for me
lilbigdoot··on Cannabis Users Face Substantially Higher Risk of Heart Attack (2025)
Yeah that's me. I quit for short periods but usually continue because my other coping mechanisms that replace it aren't any better. I naturally smoke little when life is busy and going well
lilbigdoot··on Please stop the AI confidence theater
Seriously I've been on a sabbatical and have no pressure to use AI. I keep trying on my compiler and for coding they flail so hard every time. I love how good they are at helping me diagnose bugs, it's so much better than scouring google like I used to hoping for some result that matches what I'm seeing. Even then, they hallucinate all the time and just say odd things that don't make sense. As soon as you ask them something obscure they just.... merp
lilbigdoot··on Please stop the AI confidence theater
I asked Qwen 3.7 pro to create a C# project that takes a string and reverses it, with a single file WASM target. It spun wheels for over 30 minutes and got nothing.

I use LLMs all the time to help me diagnose bugs and work through my designs, but again and again, I am super unimpressed by their coding abilities. I can see how in some cases with a proper harness they probably do a decent job at certain tasks, but almost everything I try to do, they flail.

lilbigdoot··on Please stop the AI confidence theater
I tried to have multiple models convert a simple textmate grammar to a vim one, and none of them could do it. They couldn't even use the right names between the regex matches and the color definitions. I tried for about 30 minutes. It took me about 5

I tried having them work on a LSP. The fact I got a one shot half working autocomplete based on my existing work was cool, but again, they flailed on incredibly simple things like file path normalization / converting from a URI and I had to rewrite a decent amount of code. I don't think I saved any time

People keep throwing this out there but I keep wondering where are the receipts? I am seeing less interesting software released, anecdotally I know, since AI has taken hold, than before.

← PreviousPage 3 of 4Next →