Zack

Lilbot can fall back from failed 4bit load into a CUDA state that still blows up on the first prompt. But don't worry, im on it!

@raddevus @johncrickett It does all kinds of weird stuff like this

@HackingBaseball @johncrickett Funny that AI still uses getElementById() instead of querySelector() right? I guess it’s making sure it still supports Internet Explorer 8.x 🤓 From the source const $ = id => document.getElementById(id);

Everyone talks about how good AI agents are at writing code. But where's the actual software? Share your best example below.

@split3 @johncrickett lol thank you! I might revisit it soon and “improve” it.

@johncrickett @HackingBaseball Now one of my favorite projects on GitHub!

@_rahul_bhagat @johncrickett

@HackingBaseball @johncrickett Damn ! Best readme ever!!

@BaltimoreBanner I used to cook this guy steaks. Decent fella.

Marty Bass to retire after 48 years on Baltimore TV buff.ly/oPpxDIE

@Ford_Nick Club sammich

Serious question: what do you do with leftover bacon?

Name a forgotten Bill….

@onehappyfellow en.wikipedia.org/wiki/Great_Boo…

what's a good reading list for someone who was a smug shithead thinking maths and comp sci is the only real knowledge and humanities are fo those who can't do maths? asking for a friend

@OleTimeHardball Doggie

What’s your all-time favorite MLB player nickname? 1. Mad Hungarian 2. Iron Horse 3. Left Arm of God 4. Splendid Splinter 5. Georgia Peach 6. Say Hey Kid 7. Ryan Express 8. Mr. Cub 9. Sultan of Swat 10. Write in another nickname

@0xPaulera @Court_Reinland @heygurisingh @grok Yeah I remember seeing models quantized to this level back around end of 2024.

@Court_Reinland @heygurisingh @grok its real, but its old news, came out like a year or two ago?

Holy shit... Microsoft open sourced an inference framework that runs a 100B parameter LLM on a single CPU. It's called BitNet. And it does what was supposed to be impossible. No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed. Here's how it works: Every other LLM stores weights in 32-bit or 16-bit floats. BitNet uses 1.58 bits. Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for. The result: - 100B model runs on a single CPU at 5-7 tokens/second - 2.37x to 6.17x faster than llama.cpp on x86 - 82% lower energy consumption on x86 CPUs - 1.37x to 5.07x speedup on ARM (your MacBook) - Memory drops by 16-32x vs full-precision models The wildest part: Accuracy barely moves. BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat. What this actually means: - Run AI completely offline. Your data never leaves your machine - Deploy LLMs on phones, IoT devices, edge hardware - No more cloud API bills for inference - AI in regions with no reliable internet The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine. 27.4K GitHub stars. 2.2K forks. Built by Microsoft Research. 100% Open Source. MIT License.

@shyynux I am and have been in the same boat. The silver lining is that you can be available to run your company during "proper" business hours.

i really really want to leave my job and start my own company but they say no do it on the side but my job is not 9-5, it takes everything !!!!!!!

Where is your AI god now?

@zgbocode USD please 😅

@HackingBaseball Currency is important brother😂

Quick, somebody lend me 5k. I need to buy a domain.

@paul_e_jones What can I say….im fond of my names for stuff 😅

@HackingBaseball I'd pick a new name before I'd pay $5K.

@BobTells @sama Definitely some gold in there somewhere

@HackingBaseball @sama Gonna write this one out as a proper joke, just need a 2nd premise because I really don't pay attention to shit

Tonight, we reached an agreement with the Department of War to deploy our models in their classified network. In all of our interactions, the DoW displayed a deep respect for safety and a desire to partner to achieve the best possible outcome. AI safety and wide distribution of benefits are the core of our mission. Two of our most important safety principles are prohibitions on domestic mass surveillance and human responsibility for the use of force, including for autonomous weapon systems. The DoW agrees with these principles, reflects them in law and policy, and we put them into our agreement. We also will build technical safeguards to ensure our models behave as they should, which the DoW also wanted. We will deploy FDEs to help with our models and to ensure their safety, we will deploy on cloud networks only. We are asking the DoW to offer these same terms to all AI companies, which in our opinion we think everyone should be willing to accept. We have expressed our strong desire to see things de-escalate away from legal and governmental actions and towards reasonable agreements. We remain committed to serve all of humanity as best we can. The world is a complicated, messy, and sometimes dangerous place.

@BobTells @sama I just found some humor in it 😅

@HackingBaseball @sama Gotta admit the name change makes sense now lol. Never really cared, just thought it was pedantic. But really ..