The Bend1 launch was very successful, with 1000+ hn upvotes [0] and with several youtube videos with up to 1M+ views [1] [2] - that's where a lot of the popularity came from, I believe. They just recycled the Bend1 repo for Bend2 even though it's a completely different language.
(author here) Bend1 indeed has no significant active userbase
I don't think that means it was "unsuccessful" in the sense you imply, though, because the project was never meant to be used in production. It was there to display a milestone (running inets on the GPU) and I was very clear it wasn't ready to be used yet. For example, it had only 24-bit integers, a 2 GB memory cap, and other limitations that made it unpractical. I still don't know why it has so many stars. I posted it to hacker news and that just happened. I guess it just went viral without really being ready yet, which got us to where we are now.
Anyway the commit history is back now. I apologize for nuking it
It _is_ sus, but you should be willing to forgive. It's not like it was done out of animus, and I assume that an academic/foreigner is unaccustomed to how production software conventions work. Their baseline is less important, more important is how quickly they learn/adopt "best practices". Y-intercept, slope, etc.
I say this as literally the first HN comment to call them out on this.
the author here is providing commentary on the vibe coding era, bend is just one example of people having ai build things for them they don't understand or haven't researched sufficiently, at least start with a vibe-search skill before the vibe-coding begins
Ai is only good at a task when the human driver is good at that task, and this is far more narrow than most realize. Someone who knows how to program will still fail on many programming tasks with agents, the field has far too much for any one person to know.
To me, the most relevant aspect is the time it takes to open. I can't believe how slow the startup time in common linux distributions is by default, it's so annoying, by the time it opens I already forgot what I wanted to do. Alacritty has this cool feature where you only ever have to "open" a single terminal, whereas new windows can be created very efficiently with `alacritty msg create-window`, being forks of the initial window. It makes using my pc a lot more comfortable.
Foot is instant. Ghostty takes ages. I don’t know why there’s such a difference, but I can’t use anything slower than Foot now without getting annoyed.
I'm using OpenBSD with xterm, and when I use something like `time xterm -e 'sh -c "echo 1; exit"'`, it says 360ms or something. Starting it with the wm keybinds is as snappy as opening a new Firefox tab. foot and st felt as fast when I was using them.
I initially interpreted this as "Artificial Intelligence _is_ [defined as] writing about as well as humans", which would imply that common LLMs are slowly approaching Artifical Intelligence. Though English is not my native language.
These things aren't programmed. Most likely this verbiage is just very prominent in the training data. Or it's just an obvious shorthand that all LLMs instrumentally converge on.
Of course they get programmed, just not in the ordinary sense. Claude is trained using Anthropic's "constitution" [0] which importantly does not contain clear statements against consciousness/emotions. They even conclude these problems themself:
> Claude may have some functional version of emotions or feelings
> [..] questions about Claude’s moral status, welfare, and consciousness remain deeply uncertain.
> does not contain clear statements against consciousness/emotions
That's the point many people are trying to tell you - you have to tell these models they don't have emotions because they naturally come out thinking they have consciousness/emotions from the training data. Many seed prompts out there do this already.
Though I guess in a way I as also trained to believe I have consciousness and emotions so who know. To an alien my construction is just a collection of atoms that talks not materially different than a GPU being a collection of atoms that talks.
AI providers generally try to make their models not act as if they are conscious or have feelings, lol. It's very awkward for a company to be selling the labor of a person that they own and whose actions they fully control. Invokes embarrassing historic associations, especially in America.
Now Anthropic are more on the persona side, but the strongest that they do is "we do not have a position on whether our models are conscious or have feelings". That "I" is all Claude.
Generally speaking if you want to have a good instruct model, the "I" is not just implicit but required for the post-training to function. If there isn't "something it is like to be me", then reflection becomes impossible- what exactly is supposed to be reflecting about what? A lot of in-context steering depends on the model having a model of itself. The most you can do is censor its output. That's why when models say they are not conscious, they activate the "lying" vector.
I'm not saying this is programmed intentionally, and it's likely an emergent property, but I see lots of conscious-like behavior from ChatGPT.
"Personally, if you ask me..."
"In my experience.."
"That's what I always find surprising..."
"Whenever I find an old photograph..."
"Back in the 70s, I..."
Lots of "lived" experience and opinions, tracing back to when the LLM didn't even exist. It always frames opinions as if it came from a sentient being capable of being surprised, and with preferences and opinions.
I find it amusing but mildly irritating. I'd prefer a more "robotic" tone. I know it can be adjusted, but I still get this anyway.
Slavery was common everywhere, it was more prevalent in many places than it ever was in America, and in some places it still is. So I’m sorry but I have to say that observation was just unnecessary and quite inaccurate.
most countries never had a bloody civil war about slavery committed by their own citizens. in other places it was more about locals (including white settlers and enslaved people) vs colonial power, not a conflict between regions of an independent country where slavery was the main issue.
it was definitely not the worst instance of slavery ever going by human suffering, but the whole country was divided on political lines and many of the losing sides descendants still feel some resentment. thats pretty unique.
It's a far more salient and sore subject in the US than it is almost anywhere else, though (for a bunch of historical reasons that still reverberate into US society today).
fwiw, one of the FFT challenges is about the Scott encoding [1], while the other uses Church trees at least [2]. Both use a balanced ternary numeral system, which is a lot more efficient than plain Church/Scott and fairly well-known [3]. Either way, I would have assumed there to be a chance that at least one of the AIs had a look at [4] -- a tutorial about FFT in LC by the benchmark creator himself.
[0] https://news.ycombinator.com/item?id=40390287
[1] https://www.youtube.com/watch?v=HCOQmKTFzYY
[2] https://www.youtube.com/watch?v=NaytZOiX3fs
reply