https://github.com/youssofal/MTPLX If you’re running one of the new M5 Macs and you want your local LLMs to feel genuinely fast, MTPLX is worth a look. It’s a free, open-source (Apache-2.0)...
A two-part essay on the deep reasons coding is uniquely suited to AI agents, and why developers shouldn’t expect their compensation to scale linearly with their new superpowers. Part 1:...
For the last year or so, my “prompt library” was a mess of Apple Notes pages and a few snippets in Masscode. Every time I wanted to reuse a prompt with...
If you live in Claude Code or Qwen Code and want to keep coding from your iPhone or iPad without sessions dying every time the train goes through a tunnel,...
https://www.thestreet.com/markets/elon-musk-just-made-a-shocking-admission-about-tesla-stock-litigationhttps://www.linkedin.com/pulse/tesla-fsd-hardware-3-vs-4-technical-deep-dive-vikas-pandit-k23nc/ I’m not saying users shouldn’t expect FSD to just work as Elon Musk promised. But it’s unrealistic to expect a 7-year-old computer on wheels to keep up with every...
The brutal mismatch between how fast you think and how fast you can do anything about it In 1999, Bill Gates published Business @ the Speed of Thought. The premise was...
Think about the device you’re reading this on. Somewhere inside it, there’s a hard drive (or SSD) quietly holding terabytes of data — photos from five years ago, half-finished documents,...
There are now more software developers on Earth than nurses and doctors combined. That fact alone should give us pause—not because it’s necessarily wrong, but because it forces us to...
How I built a routing proxy that brings Google’s TurboQuant compression to hybrid-attention models running locally on a Mac. A month ago, Google published a blog post about a paper...
While the Western AI coding market gets all the attention, China has quietly built a parallel ecosystem of coding agents that rival — and in some cases undercut — their...
Claude Code’s plugin and skills ecosystem has exploded. There are now dozens of framework repos promising to turn your terminal agent into a disciplined engineering team. I reviewed nine of...
If you’ve been developing iOS apps for any length of time, you know the drill — you get a folder full of images and suddenly you’re resizing, converting, compressing, and...
https://merowing.info/posts/stop-getting-average-code-from-your-llm/https://agents.md Sure, one day, AI agents will be good at self reinforcement, recursive improvement, etc, all towards singularity without eating up all your credits/money overnight. But until then, help the...
https://www.businessinsider.com/meta-ai-alignment-director-openclaw-email-deletion-2026-2 We now live in a world, where if you have done something silly (or just unprofessional), you share the story, laugh about it (or be laughed at), and move...
What Has Changed (And Why You Should Care) If you’ve been using chatbots like ChatGPT, Claude, or Gemini for basic questions and answers, you’re only scratching the surface of what...
“In the old days, many decisions were simply based on some mixture of experience and intuition. Experts were ordained because of their decades of individual trial-and-error experience.” — Ian Ayres, Super...
The reason is simple: because you can — and even faster now. If you have an Apple Silicon Mac (M1 or later) with 16GB of RAM or more, you can run powerful LLMs...
Unlock 2-3x faster AI on Apple Silicon! This post explores optimizing models with Ollama and MLX, boosting performance for demanding applications.
https://exolabs.nethttps://github.com/exo-explore/exohttps://www.jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5 If you have about 40-50k USD for 4 Mac Studio with 512GB RAM each, you can run your full DeekSeek at 32.5 t/s. Probably the cheapest way to do...
https://www.the-independent.com/tech/google-gemini-vs-chatgpt-cloudflare-ai-b2881240.htmlhttps://x.com/Similarweb/status/1942838749588775302 Gemini is growing fast. Back to the “Just Google It” days soon. Now waiting for Meta to find a way to make AI relevant or useful in social. Same...
https://www.youtube.com/watch?v=21EYKqUsPfghttps://www.youtube.com/watch?v=7u-DXVADyhchttp://yann.lecun.com/https://www.wsj.com/tech/ai/yann-lecun-ai-meta-0058b13chttps://techcrunch.com/2025/11/18/hugging-face-ceo-says-were-in-an-llm-bubble-not-an-ai-bubble/ Yan LeCun been saying this many times since ChatGPT, LLMs can’t get us to AGI. It’s not just about him leaving Meta, or Mark Zuckerberg getting a 28 year...
The reason is simple: because you can. M1 or later Macs with 16GB of RAM or more are powerful enough to run useful models on device without sending any data...
https://www.wsj.com/business/openai-oracle-sign-300-billion-computing-deal-among-biggest-in-history-ff27c8fehttps://nvidianews.nvidia.com/news/openai-and-nvidia-announce-strategic-partnership-to-deploy-10gw-of-nvidia-systemshttps://www.youtube.com/watch?v=bircUYzIlMg OpenAI is still trying to maintain its lead in the AI sector. It recently partnered with Oracle on a multibillion-dollar deal and secured a substantial investment from Nvidia. Yet...
Lightweight, private, and customizable retrieval-augmented chatbot running entirely on your Mac. Based on the excellent work by pruthvirajcyn and his Medium article. ⚙️ About This Project This is my personal...
https://mistral.ai/news/voxtral Mistral has unveiled Voxtral, an exciting new AI audio model that positions itself as a strong open-source competitor to Whisper, the reigning champion of speech recognition. With claims of...
https://www.wired.com/story/sam-altman-meta-ai-talent-poaching-spree-leaked-messages/ It’s still too early to declare a winner in the AI arms race, but one thing is clear: the competition is accelerating, and OpenAI may struggle to maintain its...
https://machinelearning.apple.com/research/illusion-of-thinkinghttps://futurism.com/apple-damning-paper-ai-reasoningAnother article about AI is not “reasoning” – https://www.zdnet.com/article/ais-not-reasoning-at-all-how-this-team-debunked-the-industry-hype/ While it may seem that Apple is disrupting the AI industry by releasing this paper, it’s crucial for everyone to understand...
https://www.nber.org/papers/w33777https://futurism.com/time-workers-save-ai-jobs A research working paper pointing to LLM not having a big impact. And not improving salary even if it helped with productivity of workers. It’s just 2 years in...
https://bgr.com/tech/17-insane-veo-3-ai-videos-thatll-stop-you-from-trusting-anything-you-see-online/
https://www.bbc.com/news/articles/c1dr6neg766o I am sure there are people building these already, browsers fully integrated with LLMs, etc. But allowing OpenAI to just buy up access to 64% of web usage just...
