unleaded

Who's their biggest rival? Roblox doesn't support Linux either.

I don't get the part about having the AI write commit messages. Is it that hard writing them by hand? Looks 100x better plus saves potential embarrassment if the AI says something stupid. It seems very common though so maybe I'm missing something.

Yes and several other models that know about the answer don't... not sure what you're trying to break

For most cases probably not. It's just something I like testing new models on sometimes, the pelican riding a bicycle benchmark probably isn't that useful either.

I think most thinking models can do it to be fair, I think when I tried this it was all with non-thinking models/modes. Wasn't trying to make a point that LLMs can't do it or anything, just thought it was weird.

What does it say to the second question? I've found Claude is one of the worst models with regards to pop culture knowledge like this, even compared to the Chinese open ones. Just curious, not really relevant to the initial post but I don't pay for it so I only have access to Sonnet.

https://claude.ai/share/5e7e09b2-a75a-4024-b261-9a1a4e063a8b this is mostly hilariously wrong. wrong tie colors, they did not replace their bassist with a drummer, two completely made up albums, the rob cantor song it is thinking of is "shia labeouf", and a few fan behaviours i think it just made up

I don't think it's solved this fundamental architectural problem by itself, it will have just squeezed the edge cases thinner. It keeps happening, people find a question it gets stupidly wrong, the vendors proclaim they've fixed it, then another one gets found.

This reminded me of some weird quirk/experiment I found with LLMs that I found while messing around, maybe someone can explain it or something.

Open any AI chatbot that isn't cheating by connecting to the Internet (so disable web search). Claude, DeepSeek, Kimi, whatever. Ask them this question:

"What was that weird band from michigan from the 2000s that wore coloured ties"

You will probably get a wrong answer, or if you're lucky you'll get a string of wrong answers with "wait, no - it's definitely..." before it gives up. If you aren't familiar with the band the question is referring to you might be fooled into thinking it's a tough question, but it really isn't. There is only one band that could possibly meet this criteria, you can even put the question into Google search and their Wikipedia will come up as the top result.

Then, open a new convo and ask:

"Who are Tally Hall"

The AI will easily tell you that they are a band formed in Ann Arbor, Michigan in the 2000s, known for their quirky sound and their gimmick of each member wearing a colored tie, even giving the correct color for each of them most of the time. Very odd.

I'm guessing this is a vibe coded shell + some apps over the CE kernel? Never seen any version of CE that looked like that.

it might be dumb but it really breaks my heart seeing cool hack projects like these being vibe coded. Like they've thrown away some opportunity or something i can't really articulate why

i think even the icons are drawn by claude which explains why they look so strange https://github.com/maximqaxd/wince-dc/blob/c929784ba13226cc3...

I just tested it with some risc-v code and it wrote down a "mov" instruction several times.. yeah something needs tuning maybe

  .\llama-server.exe -m ..\Qwen3.6-35B-A3B-UD-Q4_K_M.gguf -ngl 999 --n-cpu-moe 41 -c 262144 --port 8081 --flash-attn on --cache-type-k turbo4 --cache-type-v turbo3 --no-mmap --mlock --host 0.0.0.0 -t 8 -tb 8 -np 1

Haven't had much time to test it other than asking a few questions & changing some HTML in cline so it might be thick as a brick for all I know, but still worth trying

Qwen3.6-35B-A3B-UD-Q4_K_M runs at about 11 tokens/second on my poor old 1060. Absolutely nuts how far we've come

As someone who doesnt use these tools, why does every AI company need their own version of Claude Code? Is there more to it than vendor lock-in?

Open Watcom is still actively developed! Worth looking at.

old thinkpad X series is a good place to look

LLMs are surprisingly good at dealing with ancient APIs, even terrifying things like VBScript and ActiveX in IE5 (usually with a condescending disclaimer at the end of the response). With a manual on hand to double check it can be helpful sometimes. Gemini (only one I really tried) is very knowledgeable about DirectX 5.

I don't like the idea of vibecoding esoteric stuff though. I feel it kind of ruins the magic of these things when you have Claude bang it out in an afternoon, especially if your project idea is more art than anything. There have been a few vibecoded weird doom ports posted on here before, obviously its just how i feel but it seems like a wasted opportunity.

What a stupid disclaimer. "we have spent billions developing this technology and marketing it as smarter than 99% of humans, we put it at the top of nearly every search page, but it's all just for funsies. you're not actually supposed to use it, duh"

Strong AI enthusiasm like on there and poor taste tend to correlate pretty strongly. I'm sure there are lots of developers using LLMs to assist with the boring work of coding and keeping mostly quiet about it, still keeping it on a short lead & doing the more creative parts themselves. There have always been indie developers who hate coding and see it as just a necessary step to get their idea out the door, and they still make good games. All the dialogue in Undertale is implemented in a giant 5k+LOC switch statement.

I really wish CSS added an option to set font antialiasing and hinting. Would make all these old windows style websites look 1000x better.

This is mostly the fault of the model, a lot of them have been trained to generate HTML in a specific style. Claude's is pretty distinct for example, I think the new DeepSeek copies it. Some of them can generate more humanlike HTML like Kimi K2 IIRC, which I feel is the model with the least amount of post-training in general.

It's necessary if you don't want it to generate HTML with images and other assets you don't have of course, that's why they use emojis or meticulously handcrafted SVGs, or WebAudio synthesized sound which pretty much no humans did before.

https://www.nicovideo.jp/watch/sm2796083

It's easy when it's the only way to get things done. Think about how nobody who was learning programming before 2023 was seriously thinking "This would be so much easier if the computer wrote it all for me".

Thank god for the 386.

I think 480p resolution can look a lot better than people make it out to be. I reckon people's perception of it has been warped by YouTube serving dreadful low-bitrate 480p video for years.

It's too late to decide not to do business with them once they've stopped you from using a product you already bought.

Wiki Workers United is the union for the paid staff of the Wikimedia Foundation, not volunteer Wikipedia editors.

thank god the 2003 source leaked too!

https://gitgud.io/aeroshell/atp/aerothemeplasma

The idea that humans could "work like" LLMs (or vice versa) is very vague and can be stretched to say pretty much anything. It's a pointless question IMO. I don't think I do, but maybe I really do on the inside and my consciousness makes me think I don't! We don't know.

The Full Tilt version also has multiball which is missing from the Windows version. Lock a ball by shooting into a wormhole where the two lights are the same color, lock 3 balls to start.

If you enjoy playing Space Cadet I would really recommend giving Visual Pinball a try. There are so many more pinball games better than Space Cadet, with amazing tables people have made for them all available for free. I think it's Windows only though (very, tables are all scripted in VBScript and PinMAME is loaded as a COM object).

As an aside I tried to hack around with this and found out the programming for Space Cadet is pretty awful (not to disparage them or anything, it works). The state of the lights directly reflects the game state. (This is the cause of the bug where if you drain or start a mission while the rank-up light show is playing, you can skip a rank.)