Make invalid states unrepresentable (for your agents) | ⌨️🤷🏻♂️📷
The Short Leash AI Coding Method For Beating Fable
Critical AI
Critical AI Literacy (CAIL) from my perspective.
Deepseek drops another HUGE breakthrough
DSpark by Deepseek. Huge speed and throughput unlock. #ai #ainews #...
AI has torched the market for junior programmers | Seldo.com
Junior programmers are getting destroyed by AI — down 19%, while devs over 40 thrive. Meanwhile, millions of non-developers are shipping real software without the job title. The credential market collapsed; the activity exploded. The problem: nobody's building the next generation of senior engineers.
There Are Three Types of AI Users
What will differentiate people is not how smart they are but their relationship to mental effort.
I'm Begging You to Leave Your AI Note-taker at Home
Stop Bringing Your AI to Coffee
altic-dev/FluidVoice: FluidVoice - Fastest macOS Offline Dictation app - Voice to Text fully Local. One ⭐ takes us a long way :))
FluidVoice - Fastest macOS Offline Dictation app - Voice to Text fully Local. One ⭐ takes us a long way :)) - altic-dev/FluidVoice
Karpathy CLAUDE.md Grows to Ten Rules: New Self-Check Protocol for AI Coding Loops
Karpathy CLAUDE.md ten rules: a document attributed to Andrej Karpathy began circulating Friday, adding six agent self-check rules to the community four-rule template. It covers verification before...
Micro-Agent: Beat Frontier Models with Collaboration inside Model API | vLLM Blog
How vLLM Semantic Router turns vllm-sr/auto into a bounded micro-agent runtime for Confidence, Ratings, ReMoM, Fusion, Workflows, and benchmark-shaped collaboration.
What happened after 2,000 people tried to hack my AI assistant — Fernando Irarrázaval
inkeep/open-knowledge: Beautiful, AI-native markdown editor and LLM Wiki
Beautiful, AI-native markdown editor and LLM Wiki
Using Local Coding Agents
Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions
Alisa’s book of LLMs
Neural net basics
The next paradigm shift (according to Karpathy) - YouTube
Anthropic released Claude Tag this week and while at first glance s...
The Coming Loop
Loops, harnesses, and why even loop skeptics may end up with them.
The Coming Loop | Armin Ronacher's Thoughts and Writings
Loops, harnesses, and why even loop skeptics may end up with them.
herald-email/herald-mail-app at terminaltrove
Herald is a terminal email client and inbox cleanup tool with IMAP, AI-assisted triage, MCP tools, and SSH/browser-friendly app modes. - herald-email/herald-mail-app
Local Qwen isn't a worse Opus, it's a different tool
We've all heard people say that Qwen is near-Opus level, but I have receipts and am here to be transparent with you.
oMLX — LLM inference, optimized for your Mac
Native macOS inference server built on MLX with paged SSD KV caching for Apple Silicon.
srvsngh99/Krill: Fast local LLM inference CLI for Apple Silicon. 1.57x faster than Ollama, 58% less memory.
Fast local LLM inference CLI for Apple Silicon. 1.57x faster than Ollama, 58% less memory. - srvsngh99/Krill
Run MLX LLMs 23% Faster on a Mac with MTP - YouTube
Can MTP actually make MLX models faster?In this video, I compare ...
MTPLX · Run local LLMs twice as fast on your Mac
A native macOS app for local LLMs. Native MTP decoding on Apple Silicon. Twice the speed, still exact.
Running local models is good now | ✰Vicki Boykis✰
Local agentic coding has gotten great over the past few months
The honest truth about leaders who want to replace their workers with AI
"The problem tends to show up when a CEO is handed an agentic tool like Claude Code, and has it create something, which will work just fine, and thinks “oh, wait, why do we need so many people, when I can just sit here and make things work?”
This is a bad CEO."
PI Architecture EXPLAINED | Agent Loop, Tools, TUI and More - YouTube
How Pi Works: Agent Architecture, Tools, TUI, and SkillsIn this v...
devenjarvis/lathe: Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋
Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋ - devenjarvis/lathe
AI enthusiasts are in a race against time, AI skeptics are in a race against entropy
Both sides are grappling with a real existential threat, and both sides feel like they are screaming into the void. Here's how to close the gap and get everyone pulling in the same direction.
Fine-tuning an LLM to write docs like it's 1995
In my predictions for 2030 I wrote that tech writers would be using specialized LLMs, running locally on powerful hardware. I see hints of this move to “local first” among engineering pundits, but we’re not there yet, in part because of how much more powerful connected frontier models are. That doesn’t mean we can’t experiment, though. That’s precisely what I did last week, trying to fine tune an instruct model to write like a software technical writer from the 80s and 90s.
Obsidian Excalidraw 2026 Update: 15 Workflow-Changing Features! - YouTube
JOIN THE COMMUNITY & COURSES📕 Read Sketch Your Mind: https://commu...