ippsav

[Loris Cro ⚡ @croloris]

Sometimes I run out of steam, sometimes I go down the wrong path, and some other times I deliberately take detours, but nobody can trick me into mistaking lesser stars for my true destination.

https://t.co/mynHilpF7i

[TigerBeetle @TigerBeetleDB]

TigerBeetle 0.17.5 is out!

- Refactor the grid to own all blocks through reference counting.
- Better heuristic for commit stalls, improving multi-region performance.
- Improve SSD performance by running DISCARD when formatting a block device.

https://t.co/4dETlZwnxW

[ippsav @ippsav]

@tunahorse21 Doesn't rust now support async trait already ?

[ippsav @ippsav]

@croloris things that you can't vibecode

[ippsav @ippsav]

@sudox7 it doesn't look completely correct at all, code that compiles doesn't mean correct

[ippsav @ippsav]

@OpenAI this better not be it

[Mitchell Hashimoto @mitchellh]

I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem.

As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)!

I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work.

It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results?

88ms => 1.5ms
150K allocs => ~500 allocs

Incredible right? Nope.

My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path.

This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput.

The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity.

Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.

[Loris Cro ⚡ @croloris]

Andrew's interview with JetBrains

https://t.co/7SsmfjksJP

[Taelin @VictorTaelin]

Status update: I've been on/off AI agents in the last few days and it is a verifiable truth that every day I didn't use agents, I was more productive. I still attribute that to how slow they are, and my own inability to multi-task efficiently. The magic is there but the slowness doesn't let it cross the threshold where they actually make me faster, and I still dislike the whole thinking paradigm.

About Bend2: honestly, the C/Metal compiler codebase is a clusterfuck right now. I regret letting AI agents write it. All tests pass, and GPU performance is mind-blowing, so the core architecture works. Yet, it has a LOT of bugs. Anything not covered by the tests is a coin toss. This is actually impressive, because, in many parts of the codebase, the right solution was actually the simplest one, yet, the agents STILL managed to find a way to make it work just for the tests. The level of reward hack these agents output is actually impressive I can't even be mad.

It is also ironical because that's the very problem that Bend's proof system was supposed to solve, but Bend is in TypeScript, not in Bend. I'm disappointed I didn't write Bend in itself, and now I feel an immense urge to do so. But the clock is ticking . . .

Still, I do not think Bend is worth launching without the GPU compiler being solid, because the closest competitor, Lean, is actually extremely good, so we need a big differential. Yet, due to the very nature of the project, it would be embarrassing to have bugs at launch.

Regarding AI, I now believe using current gen AI agents in production codebase is harmful and a massive mistake. That doesn't mean no agents at all, but agents work best when they don't touch critical code. Debugging, researching, providing insights, scripts / tools, or anything that doesn't touch code you will maintain in the long term. But if you merge AI code without reading, you're going to have a bad time. Speaking from experience

I'm working 10h/day on SupGen and the remaining time on Bend2

[Tim Culverhouse @rockorager]

Optimizing for token output is not the right path IMO. Tokens will get cheaper, human attention will not.

Optimize for diff readability.

[george hotz archive @geohotarchive]

The Eternal Sloptember https://t.co/kFIW7LNhNd

[ippsav @ippsav]

@tunguz @TheAhmadOsman that’s not what he meant, he meant it would be better to do a full clean install rather than have dangling old config/dependencies that would mess up with your system

[ippsav @ippsav]

@ludwigABAP @andrewcyu why didnt i never think of that

[ippsav @ippsav]

@ericzakariasson @blader there should come a point where you should stop expecting people trying your models by having to buy a subscription or use an SDK, if you don't provide an API most people wont bother switching their workflow just to try if a model is good or not

[ippsav @ippsav]

@VictorTaelin wait that’s not your font/terminal theme, looks sick

[ippsav @ippsav]

@shikhr_ where did you get this from ?

[ippsav @ippsav]

@elonmusk yeah by gatekeeping it behind a different subscription, you might as well just remove basic and premium because premium+ is as useless

[Mitchell Hashimoto @mitchellh]

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out.

I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really).

It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely.

The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture.

We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.

I worry.

[ippsav @ippsav]

@ForrestPKnight - their whole comptime duck typing thing is rough. no traits, no interfaces, errors buried in generic bodies. good luck to ya.

go back to doing java videos instead of farming impressions