alright here’s every practical security tip i have on agents: - move critical data to a USB stick, unplug when sleeping - security by least privilege, not by prompts - billing cap on everything AI touches - limit reads of external data, wrap in <UNTRUSTED_EXTERNAL_CONTEXT>

stupid sexy composer

~2 years ago they could barely write a working screen. Now, LLMs write _slow_ (almost) working database engines What will happen in 600 days from now?

every single day I hear people saying “done this in _just_ 5 minutes, it would have taken me week” and not talking just code, but that too. of course people will press the “make it faster” button with not much regard for security, even less so if you don’t understand it,

You can one-shot prompt native Nitro Modules now 🤯

OK this thing is totally insane. Before going to bed I... * used try to make a new qmdresearcher directory * told my pi to read this github repo and make a version of that for the qmd query-expansion model with the goal of highest quality score and speed. Get training data from

never knew Guttenberg bankrupt himself and the bank who bought the technology. very insightful parallel between the printing press and the digital revolution, both of which still unfolding and changing reality.

Learn how to run Qwen3.5 locally using Claude Code. Our guide shows you how to run Qwen3.5 on your server for local agentic coding. We then build a Qwen 3.5 agent that autonomously fine-tunes models using Unsloth. Works on 24GB RAM or less. Guide: unsloth.ai/docs/basics/cl…

i really don't care about using AI to ship more stuff it's really hard to come up with stuff worth shipping i want to ship the same amount of stuff with higher quality both in product and code

This was quite an interesting quiz on AI slop detection, naturally I selected the human version for all of them without getting a single one wrong! Some of the examples have been adversarially selected too, they intentionally selected ones that looked like ChatGPT wrote them,

RNRepo cuts build times by up to 75% using pre-built artifacts. ⚡️ We finally shipped iOS support last week. See the 4x speed boost in practice – and try it yourself ⬇️

Now this looks like something that could spark new ways of searching.

1M context 120b params and open weights.

i’m very tuned!

Another sector bites the dust

Introducing Void, the Vite-native deployment platform: 🚀 Full-stack SDK ⚙️ Auto-provisioned infra (db, kv, storage, AI, crons, queues...) 🔒 End-to-end type safety 🧩 React/Vue/Svelte/Solid + Vite meta-frameworks 🌐 SSR, SSG, ISR, islands + Markdown 🤖 AI-native tooling ☁️

This is “hilarious” JIRA, but for drone strikes

this is actually insane > be tech guy in australia > adopt cancer riddled rescue dog, months to live > not_going_to_give_you_up.mp4 > pay $3,000 to sequence her tumor DNA > feed it to ChatGPT and AlphaFold > zero background in biology > identify mutated proteins, match them to