Lazaro Brito

@nsg650 gee.. I don't think your thread is ever going to terminate with that code 😂

I wonder why the thread isn't being marked as terminated hmmm

@revolaition @petergyang @agents $ ln -sn AGENTS.md CLAUDE.md

@petergyang yes. the standard IS agents.md though. just anthropic thats stubborn with its claude.md. I just do this and it works for me: create two files: agents.md and claude.md. agents.md is the real file, and claude.md is basically "read @agents.md"

It's pretty annoying that Codex uses agents.md and Claude Code uses Claude.md. There should be some industry standards to this stuff?

@MehdiHacks @haydendevs that one is for the elite hackers 😂.

@haydendevs Apparently the 110GHz model costs 10x more! I posted it, and someone in the comments posted a picture of their lab using one of these!!

im sorry how much?

@carllerche @geistgrail waiting on build locks because of rust-analyzer has subtracted hours from my life.

@zekramu i don't remember having issues with it until society decided git was superior. 😂

@dev_lazaro brother how’d u live with svn

it blows my mind that people are still using git.

i looked in the mirror today and decided i'm a 100x engineer now. $ claude --dangerously-skip-permissions

@mlech26l i can only afford to run gigaslop_27b_q4.

why pay $20/month for Claude if you can run gigaslop_27b_q8 on a $20k GPU rig in your living room

@SapphoSys yup, the best of FreeBSD with none of the freedom.

macOS is the best FreeBSD distro

@ChShersh C$$

I have an idea for a much better C++ but first I need to make it slightly worse. I’ll call it C++--++

@0xsachi therapy doesn’t scale. my ego needs seed funding.

Men would rather start a start up and create a product which gets crushed by Anthropic / Open AI than go to therapy

@hthieblot Rune-Server

Anyone who surfed the early web between 1995-2010. What’s the one website/app you still think about?

@astra_095 hello world 🌎

If you started coding again from zero, what would you learn first?

@adahstwt have you considered FreeBSD?

in your opinion, which OS is best for non-tech person?? -macOS -windows -Linux

@cqcqcqdx bro enabled volatile memory

deepclean your RAM

@Sosowski bro that looks insanely fun 😂

debugging macros is fun

@_imdawon i agree. they made it so much worse.

macOS Tahoe was such a mistake i still cant search for applications theres no OS for the working man anymore

@VictorTaelin yeah, that would piss me off! i've seen agents do this exact thing and then i realize i have to start deleting entire files of source code to fix it.

Just saving this here to document a story and as a self reflection on whether AI is really making me more productive Yesterday morning I found a way to complete the new HVM approach, that is much faster than before. I spent a few hours writing a spec, and then used Opus to implement. About 3k lines of C code later, everything worked and performance was incredible: 5x faster than HVM4 (stable at ~10x now). So, in one day I had outclassed HVM4. Incredible. I'd never have implemented that so fast manually. Now, enter today. I want to turn this into a real thing, but I haven't fully read the 3k lines yet. So, how do I trust it? I spent the whole day auditing the code. With AI. Several bugs found, most minor like forgetting to collect() some argument. But then I stumble upon this: λ{ inl: 1 ; inr: 1 } This was a test. But wait. This is matching on inl/inr. So the branches should receive the value of the Either. But they were numbers instead. Numbers aren't functions. This makes no sense. So why this is a test? It then stuck me. The AI completely misunderstood how function arities work. It literally assumed for no good reason that HVM5 was supposed to handle under/over-applied functions. For no good reason. I never wrote that. It never asked either. It just kinda thought "HVM is weird in some aspects, this might be one of them..." - and then it went on to implement a massive system to handle cases that should never happen to begin with. And all of that code is obviously wrong because it should not even exist. It is wrong. It is damage. And it is there. But it isn't too bad either. I just told Opus that it was wrong. Perhaps not so politely. And it solved it just fine. But then this begs the question. I spent ~20 hours in this file, and it is STILL not done. I went from 0 to 95% in the first 5 hours. Yet, 15 hours later, it is still not 100%. I suppose that is the real effect of using AI. If I had just written the C file manually in the last two days, would I not be further than where I am *right now*? Surely, the first version would have taken much longer to drop. But when I'd finish writing all that code, there would be zero, literally zero retarded shit. And, just today, I caught 5 or 6 retarded shit. And the worst part is: I don't know what the number of retarded shit left is, but I'm afraid it is >0. So if I have to read it all, review it all to ensure there is no retarded shit... what did I achieve by using AI, other than that dopamine anticipation?

@saraaa7447 my thighs just got a little warmer reading this.

Finally got myself a professional computer - a 2019 16" MacBook Pro with Intel i9!! I can't wait to see what people have been raving about with these new Macs! Here's to 10 years of use :D

@lcamtuf you seem to have taken an unusual approach here.