Announcing Grok CLI 🔥
An open-source AI agent that brings the power of @grok directly into your terminal.
Built over the weekend with a few design principles in mind:
✅ No LLM frameworks
✅ No lobotomizing models
✅ Hackable (MIT licensed)
Github link below.
Your operating system, your browser, your database engine, your web server, git, your JavaScript engine, your Python interpreter… all of these are likely written in C/C++.
I repeatedly encourage people to learn many programming languages. I do not (at all) think that C or C++ should be used systematically. I use different programming languages. If you can, use Go, Python, JavaScript, C#, Java, Zig, etc.... they are often better choices than C.
I literally just published a new book on Python programming (see Amazon). It is a great language.
However, if you are proudly broadcasting your belief that safe and performant complex systems cannot be written in C or C++, you are showing your ignorance and you are signalling that you are unable to match what countless programmers have done over decades.
And no, C programming is not elitist. Generations of teenagers taught themselves C. Working with C strings does not require a Ph.D.
A bunch of rambling about the tinybox. I don't think there's much value in secrecy.
We have the parts to build 12 boxes and a case that's pretty close to final. Beating back all the PCI-E AER errors was hard, as anyone knows who has tried to build a system like this.
Our BOM cost is around $10k, and we are selling them for $15k. We've put a year of engineering into this, it's a lot harder than it first seemed. "We don't do things because they are easy, but because we thought they would be easy" You are welcome to believe me or not, but unless you are building in huge quantity, you are getting a great deal for $15k.
On the tinygrad side, we trained our first MLPerf qualifying model on a tinybox last week. We are replacing pieces of HIP that aren't up to standard, we replaced the compiler with direct calls to comgr (5x faster compile times) and we are most of the way to replacing the HIP runtime with HSA (one level lower). This is required to make multigpu fast.
The system image shipping with the box will be Ubuntu 22.04. It will only include tinygrad out of the box, but PyTorch and JAX support on AMD have come a long way. and your hardware is your hardware. We make money either way, you are welcome to buy it for any purpose.
The goal of the tiny corp is to commoditize the petaflop, and we believe tinygrad is the best way to do it. Solving problems in software is cheaper than in hardware. tinygrad will elucidate the deep structure of what neural networks are.
We have 583 preorders, and next week we'll place an order for 100 sets of parts. This is $1M in outlay. We will also ship five of the 12 boxes we have to a few early people who I've communicated with. For everyone else, they start shipping in April. The production line started running yesterday.
I have no idea what the preorder conversion rate will be, and don't really want to do something annoying with a second stage preorder. We have funding and can YOLO into the 100 boxes. I trust we'll sell them. First in preorder line will be first offered, and after we e-mail you you'll have a week to pay or lose your spot.
HW specs: 6x 7900XTX full fabric PCI-E 4.0, EPYC 7532, 128 GB RAM, 5x 1TB SN850X SSDs (4 in raid, 1 for boot), 2x 1600W PSUs, and an empty 16x OCP 3.0 slot for networking.
It's a really nice box; I take a lot of pride in building nice things. We will use it as a platform to push the limits of what's possible, you need a standard piece of hardware to do that. Example: that fast Mixtral grok demo can be in theory done on a tinybox (the 6 GPUs have 5.76 TB/s of RAM bandwidth), but the software needs tons of work.
Someday, we want to tape out our own chips. But if you can't build world class software on AMD chip (which is a lot better than the chip you'll make), you shouldn't be messing with expensive tape outs.
We will push the limits of what's possible on this box. The hardware is solid, but the software is a huge journey. I'm excited to be on that journey together with all of you soon to be tinybox owners. To the metal. We will squeeze every last FLOP out of this thing.
I’m obsessed with learning how to learn.
So, I spent 100+ hours studying how Elon Musk, Sam Altman, and Naval Ravikant absorb information.
Here’s what I found on becoming a learning machine:
tech twitter by language
Mention Rust: Rust Foundation may sue
Mention Go: no one responds since they're working and shipping a real product
Mention JavaScript: get corrected for not using TypeScript
Mention PHP: get invited to speak at Laracon
Your operating system, your browser, your database engine, your web server, git, your JavaScript engine, your Python interpreter… all of these are likely written in C/C++.
I repeatedly encourage people to learn many programming languages. I do not (at all) think that C or C++ should be used systematically. I use different programming languages. If you can, use Go, Python, JavaScript, C#, Java, Zig, etc.... they are often better choices than C.
I literally just published a new book on Python programming (see Amazon). It is a great language.
However, if you are proudly broadcasting your belief that safe and performant complex systems cannot be written in C or C++, you are showing your ignorance and you are signalling that you are unable to match what countless programmers have done over decades.
And no, C programming is not elitist. Generations of teenagers taught themselves C. Working with C strings does not require a Ph.D.
frontend:
<input type="email" />
backend:
str.includes("@")
The only way to know if an email address is valid is to send an email.
Stop using regexes that don't let people use valid emails 😂
Gemini 1.5 Pro's 1,000,000+ token context length is incredible.
I got early access and spent my Saturday night running tests.
Here are 6 impressive capabilities I found: