People of Pi... Holy shit it's live. All my extensions & skills in one monorepo, with a fully automated CI xDDDDD Other repos will be archived, imma need some stars, folks :D You can now run: pi install npm:@howaboua/pi-stuff pi install npm:@howaboua/pi-extensions pi install npm:@howaboua/pi-skills These two are excluded from packs: pi install npm:@howaboua/pi-codex-conversion pi install npm:@howaboua/pi-skill-omarchy-help All the previous package names remain in tact, it's just the repo address that has changed. 10 extensions and 7 skills. Apparently it's all you need. Happy clanking! github.com/IgorWarzocha/howa… PS. Sorry, not quite as exciting as a model launch.

Ok, kinda caught up. It's easy to be outraged, but all this highlights is that we need a global body responsible for making models safe, working with the labs and goverments so this kinda shit doesn't happen. I don't trust the US gov't to regulate AI. On the other hand, I don't trust Dario or SAMA either - they are not a 3rd party. Also, you know where they can't place regulations in? Space. Put datacentres in space. Put your researchers in space. Oh wait...

I am away for one day and look at the shitshow I am coming back to, ooof. Where do I even begin catching up.

State of Local AI #1 ——— In lieu of Fable ban. Here’s the best LLMs of the week to run on your hardware. —— 4-8gb vram/ram 500$ - Gemma-4-qat huggingface.co/unsloth/gemma… I had someone mention it’s very good for subagent stuff —— 8-16gb vram/ram < 1k usd - Gemma-12B huggingface.co/google/gemma-… without a doubt the smartest model of its size —— 16-32gb Apple/Strix halo 1-2k usd - Diffusion Gemma26B huggingface.co/google/diffus… - on 1x 6000 it’s eating up to 600 tok/s - smallest smart MoE we have - lots of world knowledge - easy to run —— 32-96gb ram/vram (2-10k usd) - nex-n2-mini huggingface.co/nex-agi/Nex-N… builds on qwen3.6-35B and seems to do really well - qwopus-27B huggingface.co/Jackrong/Qwop… this model topped a lot of our benchmarks at local.ai —— 384gb vram (10-50K usd) - huggingface.co/MiniMaxAI/Min… 23B means it’s close to qwen3.6-27B per token, while also have a lot of specialisation. - fast inference - top open weight model on AA —— 768gb-1TB - huggingface.co/moonshotai/Ki… Kimi has always been a top player here and their last model cuts speed and cost down by 30% - great vision support - first coder model by moonshot ——— Top models: 1. Qwen3.6-35B 2. Qwen3.6-27B 3. Step-3.7-Flash 4. Minimax-M3 5. Deepseek-v4-flash ——— Budget sweet spots: #1 - 1K usd Single 3090 / Mac mini / Intel arc b70 / AMD - Qwen / Gemma #2 - 5k usd DGX Spark / Mac m5 max / 4x 3090 - qwen / Gemma step and deepseek flash #3 - 12k usd RTX Pro 6000 / Mac Ultra / 2x Spark / 8x 3090 Ds4-flash / step-3.7-Flash and above #4 - 24k usd 2x 6000 / 2x Mac Ultra / 4x Spark / Mix Same as above #5 - 50k usd 4x 6000 / 4x Max Ultra / 12x Spark / 2 H100 Minimax-m3 / nex-n2-pro / step-3.7-flash #6 - 100k usd GB300 station / 8x 6000 / 4x H200 / Mix GLM-5.2 / Kimi-K2.7 ——— Let’s keep the Internet free thanks for reading

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

I'm genuinely curious how many people know or remember that 4 days from now, claude -p and the sdk start charging api rates instead of subscription.

oh shit

Howcode mobile? Looks pretty usable to me 🤣

¬¬;

I really fucking hate when gippity just decides it knows what I'm trying to show it prior to reading the image. WTF ARE YOU GUYS DOING.

Member the good old Thinkpads? I member. Thankfully, I can afford £30 for a new keyboard. First search was £86!!! btw, it's so funny when you fire up a coding agent and it's trying to decipher a completely broken message, and it nails it. Oh, also, no, I didn't find the cheap replacement. My Clankster found it. On ebay xD Not even via browser control

Clankers are mad

WTH happened to Thinkpads. Spilled a little bit of coffee onto the keyboard and suddenly the fans go BRR and the keyboard is spitting out random things. I swear none of this would've affected my 2007 T61

BOOM. Howcode desktop will still run via whatever you have on Windows, but when you launch pi-tui mode and operate inside of the terminal, it will use WSL. Not a full WSL support, but it's close enough. I imagine full WSL support is HELL. Any tips? Or is it better to clank up a compatibility extension that will translate your bash commands to WSL paths and force a WSL mode?

"I think I need to check current files... It's almost like a little treasure hunt in the digital world!"