标签：#c

I thought it'd be interesting to use Linux PSI (Pressure Stall Information) for an LLM runtime to trim the KV cache. This is mainly useful imo for edge devices like the Jetson Orin super nano kit which have unified memory. I haven't benched much, but plan to do so more over time and see if I can make a real use of it as I run local LLMs. Let me know if it makes sense :P (I of course vibed this idea)

Your quiet space for reading articles later. Discussion | Link

The Agent Skills open standard today, and the 2026 research on agents that write their own skills. TL;DR: In late 2025, "Agent Skills" became a thing — a dead-simple way to teach an AI agent a task: a folder with a SKILL.md file (some instructions in Markdown). It's already an open standard. The wild part is what's coming next: agents that write their own skills. I built a demo where an agent solves a task the hard way once, saves a real SKILL.md , and then reuses it — cutting its total effort almost in half. ~130 lines, no API key. First, what's a "skill"? If you've used Claude Code or similar tools lately, you've probably seen SKILL.md files. The idea is refreshingly low-tech. A "skill" is just a folder with a Markdown file that says how to do something : --- name : csv-to-markdown description : Turn comma-separated text into a Markdown table. Use when the input looks like CSV and the user wants a table. --- # CSV to Markdown ## Instructions Split the text into rows on newlines and columns on commas. Make the first row the header, add a `---` divider row, then format every row as `| a | b | c |`. That's it. No SDK, no config. Anthropic introduced this in October 2025 and then published it as an open standard ( agentskills.io ) in December 2025, so the same skill folder now works across ~30+ different agent tools (Claude Code, Cursor, Copilot, and more). The full rules are short ( agentskills.io/specification ): the only required fields are name (1–64 chars, lowercase-with-hyphens, and it must match the folder name) and description (≤1024 chars, saying what it does and when to use it ). Everything else — license , metadata , compatibility , allowed-tools — is optional. That's the whole spec. The SKILL.md files my demo writes follow it to the letter, so they'd load unmodified in any compatible CLI. The clever trick: progressive disclosure Here's the smart part. If you just dumped 50 skills' worth of instructions into the agent's context, you'd fill it up and leave n

I am a big Dragon Age fan and sunk hundreds of hours into Inquisition. It had this minigame called astrariums where you had to solve these shapes based on constellation guides by tracing stars. I'm a hobby game dev and wondered if I could procedurally generate these puzzles so they were always solvable. Turns out you can, so I built a space puzzle game around it with a colorful aesthetic. I released it in web form here but I'm currently working on getting it on Steam and mobile.

I'm building TTT -- a terminal text editor and IDE written in Go. Single binary, zero config, runs anywhere. Think VS Code but in your terminal. It has syntax highlighting, LSP integration, a plugin system, an integrated terminal, git integration, etc... The source is on GitHub and I develop it with Claude Code as my pair programmer. This is the story of how a frustrating limitation turned into something genuinely useful: a built-in scripted interaction system that lets AI agents (or anyone) drive the editor like Playwright drives a browser. The problem I was deep in revamping the widget system and building out a Lua plugin API. Phases of work stacking up -- widget rendering, panel support, tree views, input fields, command registration, keybinding hooks. The kind of work where you need to see what's happening. Click a tree node, check if it expands. Open a panel, verify focus moves correctly. Run a plugin, confirm the dialog appears. Here's the thing: Claude Code can run shell commands and read files. It cannot interact with a live TUI session. The editor launches, takes over the terminal, and that's it -- Claude is blind. Step 1: tui-use (what we had) The project already had functional tests using tui-use , a JavaScript library that drives a real terminal binary. It can type, press keys, wait for text to appear, and take snapshots: const tui = await start ( " bin/ttt " , [ " test-file.go " ]); await tui . waitFor ( " test-file.go " ); await tui . exec ( " editor.joinLines " ); const screen = await tui . snapshot (); expect ( screen ). toContain ( " joined line " ); This works. But it's slow -- each test spawns the binary, waits for screen renders, polls with timeouts, and parses terminal escape codes. And critically, it can't click . Mouse events aren't supported. For a widget system with tree views, buttons, and split panels, that's a dealbreaker. Step 2: Debug commands (the workaround) So we added a Debug: Simulate Click command to the editor itself. Open the co

I've been thinking about this problem for a while. Developers and businesses need quality websites fast — but the options are either overpriced custom builds, outdated templates, or starting from scratch every single time. So I decided to build the solution myself. Softchic is a premium template and ready-made website marketplace — production-ready, built on modern stacks, designed to actually look good. This is Week 1 of building it in public. Why Softchic The market exists. Developers need templates. Businesses need websites. But most template stores are either bloated, outdated, or built on stacks nobody wants to touch in 2026. Softchic is different — every template ships with: Modern stack (Next.js, TypeScript, Tailwind CSS v4) Clean, production-ready code Premium design out of the box The name went through 25+ candidates across multiple languages before landing here. Clean, available, memorable — Softchic. The Stack Framework: Next.js 14 (App Router) Language: TypeScript Styling: Tailwind CSS v4 Components: shadcn/ui Payments: Lemon Squeezy (international) + Paystack (Nigeria) Email: Resend Deployment: Vercel Design language: dark and premium — #0D0D0D background, #2563EB blue, #F97316 orange accents. Week 1 — What Got Built ✅ Waitlist page — designed and ready to deploy ✅ Navbar — responsive, dark-themed ✅ WaitlistForm — wired to Resend for email capture ✅ Brand system — colors, typography, full design identity locked ✅ Payment architecture — Lemon Squeezy + IP-based currency detection via ipapi.co with PPP pricing for global fairness The waitlist goes live very soon. Follow me here on Dev.to — I'll drop the link the moment it's live. Early subscribers get first access when the store launches. The launch goal: 200 waitlist subscribers before opening the store. That's the benchmark. No exceptions. What's Next Waitlist page goes live 🚀 Product listing page Template preview system First upload — a SaaS landing page template The Real Talk Building a marketplace fr

Active inference: curiosity emerges for free from minimizing surprise — 48% vs 100% on a foraging task. TL;DR: Most AI agents chase rewards — they pick whatever action scores the most points. I tried a different, brain-inspired goal: avoid surprises . Something neat happened — the agent became curious without being told to. It goes looking for information before acting, and that takes it from 48% to 100% on a simple task. ~100 lines. Two different ways to make decisions Most AI agents are "reward chasers." Give them points for doing well, and they'll pick whatever action they expect to score highest. Simple and effective. There's another idea from brain science: instead of chasing points, try to avoid being surprised — act so the world matches what you expected. It sounds almost too simple, but it leads to a surprising bonus: when you're trying not to be surprised, going and finding out what you don't know becomes valuable all by itself. In other words, curiosity isn't something you have to bolt on. It comes for free. This is called active inference , and in 2026 it jumped from neuroscience into AI as a serious approach ( here's a 2026 paper ). Here's the smallest demo that makes it click. The 10-second version The task: a reward is hidden behind either the LEFT door or the RIGHT door (50/50). There's also a hint you can check that tells you which door — if you bother to look. ❌ Reward-chaser ✅ Curious agent What it cares about getting the reward, right now getting the reward + not being unsure What it does guesses a door checks the hint first, then opens the right door Success (400 tries) 48% 100% Nobody told the second agent "go check the hint." It did it on its own, because being unsure bothered it. How it works Before acting, the agent scores each option on two things: Does this get me closer to the reward? Does this make me less unsure about what's going on? value_of_checking_the_hint = how_unsure_am_i # high when it's a total coin-flip value_of_just_guessing =

Theory of Mind and the Sally-Anne false-belief test, in ~60 lines of Python. TL;DR: There's a famous test that kids pass around age 4. It checks whether you understand that other people can believe things that aren't true. I built two AI agents: one that only knows "what's actually happening" (fails, like a toddler) and one that keeps track of what each person believes (passes). It's ~110 lines, and it's the foundation for agents that can actually work together . The test Sally puts her marble in the basket , then leaves the room. While she's gone, Anne moves the marble to the box . Sally comes back. Where will she look for her marble? If you said basket , nice — you just used something called "theory of mind." Sally never saw the marble move, so in her head it's still in the basket. What's actually true (it's in the box) and what Sally believes (it's in the basket) are two different things, and you kept them separate without even thinking about it. A 3-year-old says "box" — they can't yet separate what they know from what Sally knows. A 4-year-old says "basket." It's one of the most famous tests in child psychology, and in 2026 it's become a real test for AI agents too. The 10-second version ❌ Agent with no "theory of mind" ✅ Agent that models other minds What it tracks only what's actually true what each person believes, separately Where will Sally look? "box" "basket" Result FAIL (only knows reality) PASS How it works (the whole trick) The only difference between the two agents is one rule: a person's belief only updates when that person is actually in the room to see it happen. def someone_moves_the_marble ( new_place , who_is_watching ): for person in who_is_watching : # only people in the room beliefs [ person ] = new_place # update THEIR mental picture So when Anne moves the marble while Sally is out, only Anne's mental picture updates. Sally's is frozen at "basket." Ask the simple agent and it just reports reality ("box"). Ask the smarter agent and it answer

A sleep-like phase that consolidates noisy daily experience into durable memory — 75% vs 100% recall. TL;DR: There's a wave of 2026 research giving AI a "sleep" phase — time spent not answering questions, just tidying up what it learned that day. I built a 90-line demo of the idea. The agent that "sleeps" remembers 100% of what it learned. The exact same agent without sleep remembers only 75% and gets confused by bad info. Runs on a laptop. The memory problem every AI app hits If you've built anything with an LLM, you know the pain: the model only "remembers" what's in its current context window. Once the conversation gets long enough, the oldest stuff scrolls off the top and is just... gone. Forgotten. The usual fix is "make the context window bigger." But that's like fixing a messy desk by buying a bigger desk. It's expensive, and the model still gets worse as you cram more in (a real, measured effect — more text in the window can actually lower accuracy). Your brain doesn't work this way. You don't remember every sentence anyone said today. While you sleep, your brain replays the day, keeps the important bits as long-term memory, and dumps the rest. That's how you remember "I like coffee" without remembering every single cup. A couple of 2026 papers ask the obvious question: Do Language Models Need Sleep? Their answer: giving an AI a quiet "offline" phase to consolidate memories makes it remember better. So I built the simplest version that shows why. The 10-second version ❌ Agent with no sleep ✅ Agent that sleeps How it remembers keeps only the last N messages saves a tidy summary every night After 30 noisy days 75% recall 100% recall Tricked by bad info? yes no — it goes with what it saw most often Same experiences, same noise, same memory test. The only difference is whether the agent sleeps. How it works Each "day," the agent hears facts like Alice → drinks → coffee . To make it realistic, about 1 in 5 facts is wrong (people misremember, logs have errors). Th

A tiny Darwin Gödel Machine that edits itself and keeps only changes that verifiably score higher. TL;DR: I built a small program that improves itself . It looks at the tasks it's failing, edits its own code to fix them, and keeps a change only if the change actually makes it score better on a test. It goes from passing 1 of 8 tasks to 8 of 8 — and nobody wrote those fixes but the program itself. It runs on a laptop in under a second. No fancy hardware, no API key. The old dream: software that improves itself Normally, software only gets better when we make it better. You write code, you find a bug, you fix it, you ship again. The program never improves on its own. People have wanted "software that improves itself" for decades. The classic version (called a "Gödel Machine") had one rule that made it impossible to build: before the program could change a line of its own code, it had to mathematically prove the change would help. Proving that about real code is basically impossible, so the idea never worked. In 2025, researchers found a way around it with the Darwin Gödel Machine . They dropped the "prove it first" rule and replaced it with something every engineer already trusts: Try the change. Run the tests. If the score went up, keep it. If not, throw it away. That's it. It's basically how we all work — make an edit, run the test suite, keep what passes. The twist is that the program is the one making the edits. In the real paper, this let an AI coding assistant improve its own tooling and jump from solving 20% to 50% of a hard benchmark of real GitHub issues. I wanted to actually see this happen, so I built the tiniest version I could. The 10-second version Start After improving itself What it can do only uppercase learned 6 more skills on its own Test score 🔴 1 / 8 🟢 8 / 8 Who wrote the fixes? — the program did Start: ███░░░░░░░░░░░░░░░░░░░░░ 1/8 (only knows: uppercase) +reverse ██████░░░░░░░░░░░░ 2/8 +dedup_csv █████████░░░░░░░░░ 3/8 +sum_csv ████████████░░░░░░