8 reasons to turn down the transmit power of your Wi-Fi – Metis.fi
metis.fi
Link Blog
AI/ML 101
Academia 38
Design 86
Engineering 37
Entrepreneurship 17
Hobbies 26
How To 113
Productivity 535
Programming 222
Robotics 121
Software Engineering 230
March 2026
-
01-03-2026
-
01-03-2026
-
01-03-2026
-
01-03-2026
-
01-03-2026
12 At-Home Libraries to Inspire Any Bibliophile
zillow.comFrom cozy to towering, at-home libraries come in all forms. Get inspired with homes across the country.
Linked are some great ideas for libraries and home decor. I have lots of shelves in my house, but not enough!
February 2026
-
28-02-2026
Animated GIF optimizer and compressor
ezgif.comFree online tool for optimizing animated GIF images to reduce file size. Compress GIFs with LZW compression, reduce colors or frame rate, remove duplicate frames.
Linked is a tool for folks using animated gifs! Not many of us left? Anyway, this will optimize them.
-
27-02-2026
Full Report: What Claude Code Actually Chooses — Amplifying
amplifying.aiSystematic analysis of how AI systems make decisions — from product recommendations to developer tool choices.
Linked is an interesting report on how Claude code picks tools, frameworks and packages to solve whatever it’s working on. And it often decides to just build something itself!
-
23-02-2026
We Are Finally Off Discord
learncodethehardway.comWe are finally off discord and on a self-hosted system that should be better suited.
Linked is a great and detailed post about moving off discord and what to choose instead
-
11-02-2026
Building the Panama Canal
experienciasmuseodelcanal.orgLinked is info about the engineering of the Panama Canal from the canal museum in Panama City.
January 2026
-
31-01-2026
How does AI impact skill formation?
seangoedecke.comLinked is an insightful article commenting on a new anthropic paper
-
27-01-2026
Andrej Karpathy (@karpathy)
xcancel.comA few random notes from claude coding quite a bit last few weeks.
Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.
IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.
Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.
Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.
Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.
Fun. I didn't anticipate that with agents programming feels more fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.
Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.
Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.
Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows a lot.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.
Linked is an article with just observations of what it’s like to code with LLMs. In this case, with Claude. For me the observation are insightful and match my experience pretty well
-
23-01-2026
karpathy/nanochat: The best ChatGPT that $100 can buy.
github.comThe best ChatGPT that $100 can buy
Linked is a local LLM that looks very interesting. Although I dont know yet what it is or how I would use it.
-
14-01-2026
Convert Fusion Diagrams to URDF
github.comA Fusion 360 Script to export URDF for ROS 2, mentioned in the book Mastering ROS 2 for Robotics Programming - runtimerobotics/fusion360-urdf-ros2
Linked is One of several fusion 360 Script to export URDF for ROS 2
-
14-01-2026
Claude Code Everything You Need To Know
github.comThe ultimate all-in-one guide to mastering Claude Code.
Linked is one of various Claude tips collections. From setup, prompt engineering, commands, hooks, workflows, automation, and integrations, to MCP servers, tools, and the BMAD method—packed w...
-
14-01-2026
Tiny, robust useless box! by Jori | Download free STL model | Printables.com
printables.comLinked is one of m any "Useless Boxes". Very cute idea.
-
14-01-2026
Circuits - Tinkercad
tinkercad.comBring your 3D designs to life with Circuit Assemblies using Tinkercad.
Linked is Tinkered Circuits, a fairly approachable circuit design environment. Free.
-
14-01-2026
Gridfinity Generator
gridfinity.perplexinglabs.comParametric gridfinity generator. Generate custom gridfinity bins and baseplates, openGrid components, multiboard, and honeycomb storage wall then download the STL or place an order to purchase.
Linked is Gridfinity Generator. It's one of several tools to generate a large variety of compatible and interoperating containers. Very slick.
-
14-01-2026
ServBay - The best local PHP Python Node.js MySQL PostgreSQL Ollama web development environment Mac PHP Brew MAMP XAMPP Node.js Wordpress Install
servbay.comA multifunctional web development environment that integrates web servers, databases, and various programming languages. It offers multi-instance PHP running, powerful CLI support, and flexible domain and SSL customization, aimed at optimizing web and PHP development processes. Its efficient development environment enhances resource utilization. It includes software such as MySQL, MariaDB, PostgreSQL, PHP, Redis, etc., supports Docker, Node.js, and focuses on security, ensuring a smoother and more efficient development process.
Linked is ServBay - ServBay is an integrated local web development environment management tool. Very slick.
-
14-01-2026
Download Handy | Handy
handy.computerDownload Handy - the free and open source speech to text application for Windows, macOS, and Linux
Linked is a free transcription program. It got strongly recommended. When I played with it it seems pretty good by default. I've not tried the more advanced models though.
November 2025
-
10-11-2025
dfki-ric/better_launch: A better replacement for the ROS2 launch system: intuitive, simple, memorable.
github.comA better replacement for the ROS2 launch system: intuitive, simple, memorable. - dfki-ric/better_launch
Linked is an alternative to the awful ROS2 launch process. I have not tried it yet but I like the sound of it!