software working on https://xitter.cf/t.co/uUGlD1N185 gpu kernel and inference optimization

Santa Cruz, CA
Joined October 2008
rain retweeted
log4j
@log4jOct 24
2027 will be an incredible year for you if you’re technically gifted, neurologically forked and have access to exogenous focus enhancers 2027 for everyone else will be, idk, just be there for them (nothing changes for the amish)
33
104
6
1,686
45,759
We have our first offer received through applystead
10
5
144
4,564
rain retweeted
Ronald Reagan eats the same Big Mac as you Tim Cook uses the same iPhone as you the NSA runs the same abliterated GLM-5.3 as you
44
192
17
4,989
107,374
The only way to prevent garbage in prod now is to make sure that people understand what they are pushing, and there is no way to enforce that other than hiring smart people you trust to do things properly, which you should have been doing anyway rather than feeding egos
8
13
2
199
3,318
8
126
10
1,994
33,677
she's a 7 but hey that's 3 more than a root CA private key
13
482
13
8,492
81,845
Todays internet fun is brought to you by the number 4
I don’t understand? How
19
706
11
9,982
132,727
You can just do things
Readers added context they thought people might want to know
This is not built by Farhan, instead it is a screenshot of a video from the original creator @trunarla. x.com/trunarla/statu…
96
88
37
2,579
417,279
Replying to @ASUS
@ASUS fix my 150,000 USD paperweight
18
15
6
109
12,918
The craziest thing happened to me in an interview yesterday. I interviewed my first deep fake candidate. It took me a bit to catch on. My coworker noticed his glasses looked off.... there was a second ghost frame smeared across his cheeks. He'd been running a live face filter the whole interview So I asked him to put his hand in front of his face. He put it up right NEXT to his face lol, never in front. Asked again, still wouldn't do it He looked a little different from his linked in and his github (which I wont link here) hiring and interviewing is so ridiculous now. In the days of AI we're going to have to be more careful.. and forced to move to in person interviews.
161
398
41
4,371
556,264
We’d have ai a decade earlier if men realized women have been RLHF’ing their bf’s since the beginning of time
3
1
24
1,234
Psh I was running local models on PS5 boards before it was cool.
NOT EVEN THE PLAYSTATION 5 IS SAFE 🚨 Someone jailbroke a PS5 and got Qwen 3.8 27B running on its GPU at 20 tok/s. That's a real 27B AI model running locally on a games console. The same model on the PS5's CPU did about one token a minute. Meanwhile, DDR4 prices are up 24% in 3 months, AMD just raised GPU memory prices, and 5090s are basically gone. PS5 coming to a datacenter near you.
34
21
4
368
23,508
rain retweeted
something that keeps bothering me is how some people see slop as something that is happening to them, like they're some kind of helpless bystander powerless to do anything about it excuse me but you are a software engineer, you literally learned how to make sand think and make computers do your bidding?! and now you can't do anything about it? please the 2 things you should know to cut through all the noise: 1. you need to give your agent a way to verify its own work (i just posted about this so won't rehash) 2. your codebase is memory the 2nd is not new either, we have always had lint rules, compilers with good diagnostics and strong type systems, LSPs, etc to help us write better code. there is no difference when agents write the code instead, you just need more of them, and stronger ones. forget rules and skills. you can add those later. yes, your codebase is a form of memory to agents! agents love extending what already exists. so every nit and every annoyance you've ever seen, every mistake and bad pattern you observe from agents, needs to turn into a constraint, or the agents will just keep repeating those same mistakes like a virus in your code. then you keep observing and repeating this process until your codebase is locked down enough that even agents with little context can one shot a high quality PR. an even better direction is to refactor/rewrite your code such that agent anti-patterns become categorically impossible. use type systems to your advantage, use libraries/frameworks that reduce the architectural search space, or heck, create your own framework like we did for grok bot and design high quality primitives and well thought out APIs
the slop conversation is so one sided, it's not just that you can produce more code you can also observe, debug, and refactor more code even if the code is slop you have such good tools to deal with it. even if you write code manually, it's still 100x easier to maintain it
234
339
103
4,625
329,686
Introducing ManimGX, the 3D animation engine for agents. - Blazingly fast: 90× faster than ManimCE - Rust + wgpu core - Compatible with Manim's Python API - Lightweight: one pip install, no system dependencies Open source: github.com/academa-labs/mani… Docs: manimgx.academa.ai For 40 years we built GUIs for humans. Now we build APIs for agents. Try it. Paste this into your favorite coding agent: "Follow manimgx.academa.ai/llms.txt to make me a 3D animation of the solar system, and open it."
96
308
68
3,344
257,625
perhaps this one's too spicy to post tonight....
51
12
10
247
20,354
Replying to @ThomBrady5
I’m a former Apple Engineer, I’ve been working remote for over two decades (including over a decade for Apple) I cut my teeth on stage0 gentoo installs in the late 2000s and I’m a security-conscious Qubes-maxxer now. Most of my professional experience late has been frontend engineering/react but I’ve been all over the stack in my time professionally and at home. I’m learning GPUs, I just built a Dual RTX6000 pro rig running Qubes for fully private local inference. I love America, and hate the American government because it has strayed from the founding ideals expressed in the Declaration of Independence. If any of this sounds interesting, hit me up, I’m currently looking for something new after I finish up chemo next week (prognosis good).
1
17
357
Ten years of Sad Affleck memes and it turns out he'd just been trying to install CUDA drivers the whole time.
58
1,155
67
15,469
271,426
rain retweeted
this site basically models drug usage. people have different tolerances for what they can take. but everyone has a tipping point. the attention works both ways. it starts changing how they behave, how they react, for better and worse. be extremely cautious of this effect.
4
9
114
3,719
If you want to know who survives AI, look at what happened to Hollywood in the 1970s. Movie Studios used to enforce tight “shooting ratios”; usually 5:1, maybe 10:1 TOPS. As in, for every 5 feet of film shot, at least 1 foot had to end up in the final cut (35mm was expensive!) In the 70s, there was a rapid elimination of production constraints. Improvements in film cost and camera portability made the old studio rules…obsolete. Why not take multiple angles, roll simultaneously? Set could have 3, 5, even 10 cameras rolling at once. Shooting ratios *exploded*, 50:1, even 100:1 (Apocalypse Now)! Of course, it also *radically* changed the workflow. Editing use to be the quiet, thankless job in the studio years (30s-50s). Suddenly, they became the most important people on the totem pole! How do you find the masterpiece hiding in the (literal miles) of film? A ton of the footage was…trash, of course. But as each individual camera because *less* important, it opened up directors to take on significantly higher risks. Now, don’t get me wrong. Insane shooting ratios were still *kinda* a niche in the 70s. More traditional directors stuck with only slightly inflated shooting ratios (15:1, 30:1 common); it was the more experimental pioneers (Coppola, Scorsese, etc) that hit the big 100:1 numbers. The huge ratios were still crazy. Until they weren’t. You can probably guess what happened in the early 2000s. Digital cameras reduced the cost of individual footage to a complete non-constraint. Effectively free, don’t even cut on set, just keep the camera rolling. Suddenly…*EVERYONE* starts shooting 100:1. Entire new forms of content get created, like Reality TV, where ratios can hit 500:1! Massive shift of human labor to the editing side. I’d say, we’re currently in the “1970s Hollywood” of AI. It can be easy (and cheap!) to produce things (code, tools, etc), but YOU have to be the ruthless editor. It’s the “miles of film” problem all over again. Hollywood solved it by throwing massively more resources on the editing side, and editing became a “constantly talking with the director about vision/direction” job, instead of a “hide in the back office and do your work” job. It’s a hunch, but I’d bet that filmmakers closer to the experimental 1970s “ratio explosion” directors handled the later 2000s digital shift *much* better, because the underlying principles were the same. They’d certainly be ahead of the curve predicting it, and (hopefully) were less surprised when the digital ratios did hit. I’m not saying AI is exactly the same problem. But it’s a good idea to look at parallels in history where rapid elimination of constraints changed an industry, and how that industry handled it 5, 10, even 50 years later! When something starts to get cheap…helps to imagine what would happen when it’s free!
150
400
93
4,470
207,843
this is the future of software development. it really is
1
2
48
2,960