151
Coding expertise is going to collapse from AI reliance
The need for ongoing friction in long-term skill formation.
Most cited
Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 207 posts.
152
How I write software with LLMs
Lately I’ve gotten heavily back into making stuff, and it’s mostly because of LLMs. I thought that I liked programming, but it turned out that what I like was making things, and programming was just one way to do that. Since LLMs have become good at programming, I’ve been using them to make stuff nonstop, and it’s…
153
Agentic Engineering Patterns
Patterns for getting the best results out of coding agents like Claude Code and OpenAI Codex. See my introduction for more on this project.
154
There are no instances in ATProto
Like RSS and Google Reader.
155
Warranty Void If Regenerated
Tom Hartmann had not planned to become a Software Mechanic.
156
USB Cheat Sheet (2022)
I spend time investigating a non-existing bug today because I misunderstood a USB term. So I made myself a cheat sheet. Maybe it will save time to someone.
157
Where to Find the Colors Your Screen Can't Show You
An atlas of the vibrance of the real world
158
The ChatGPT/Codex app bundles a full copy of LibreOffice
I was poking around in my ~/.cache/ folder using OmniDiskSweeper when I spotted something interesting. The OpenAI Codex desktop app (since rebranded to just ChatGPT) has 1.7GB of stuff in …
159
LG to ban residential proxies from smart TV apps
The home appliance giant LG Electronics USA said this week it plans to suspend any apps built for its smart TVs that turn one’s television into an always-on residential proxy node. The move comes less than a month after researchers found that more than 42 percent of games and other apps available for download on LG’s…
160
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
For anyone who has been (inadvisably) taking my pelican riding a bicycle benchmark seriously as a robust way to test models, here are pelicans from this morning’s two big model …
161
Kimi K3, and what we can still learn from the pelican benchmark
Chinese AI lab Moonshot AI announced Kimi K3 this morning, describing it as their “most capable model to date, with 2.8 trillion parameters”. It’s currently available via their website and …
162
There are no "rogue" AI agents
Identifying them as such only lets companies like OpenAI off the hook.
163
Writing code is cheap now
Writing code is cheap now - Agentic Engineering Patterns
164
Sam Altman's response to Molotov cocktail incident
Here is a photo of my family. I love them more than anything. Images have power, I hope. Normally we try to be pretty private, but in this case I am sharing a photo in the...
165
Improving Heuristics for A* Pathfinding
On my Introduction to A* page I cover the basics of the A* graph search algorithm for finding shortest paths. Here’s an example from the town of Denerim in Dragon Age Origins. Try moving the start and goal to see A* in action:
166
167
Running Claude Code dangerously (safely)
How to run Claude Code with the `--dangerously-skip-permissions` flag in a safe way
168
Separating the Wayland compositor and window manager
Traditional Wayland compositors have a monolithic architecture that combines the compositor and window manager into a single program. This has the downside of requiring Wayland window managers to do the significant work of implementing an entire Wayland compositor as well.
169
The RCE that AMD wouldn't fix
Following backlash, AMD agreed to fix an MITM RCE I discovered in Ryzen Master. All in all, it took them over four months to roll out the fix.
170
What even is an OS now?
Computers now work the way I thought they did when I was 8. What does computing look like when most applications have an audience of 1-2 people? I'm leaving Fly.io to build a phone for that world.
171
172
Are the costs of AI agents also rising exponentially? (2025)
There is an extremely important question about the near-future of AI that almost no-one is asking. We’ve all seen the graphs from METR showing that the length of tasks AI agents can perform has been growing exponentially over the last 7 years. While GPT-2 could only do software engineering tasks t
173
The experience of rendering Arabic typography and its technical debt
Once upon a time, a frontend ticket landed on my queue which was not properly mine, but the only other Arabic reader on the team was on leave. It went roughly as follows; a block of mixed-content Arabic prose on the …
174
Why I didn’t sign the Fields medallists’ letter
[This post has been cross-posted to Terence Tao’s blog.] When I was around 11 I heard for the first time about Fermat’s Last Theorem. I was immediately captivated by the problem stateme…
175
The fall of the theorem economy
How AI could destroy mathematics and barely touch it
176
I vibed a proof of Conway's conjecture
You can just prove things, apparently.
177
Vulnerability research is cooked
Vulnerability discovery has always been gated by elite attention. Elite attention is now abundant. What happens next?
178
Jujutsu megamerges for fun and profit
A practical guide to creating and maintaining powerful megamerge workflows in Jujutsu for faster, conflict-free development.
179
SQLite as a Document Database (2020)
However recently it added a killer feature: generated columns . (This was added in 3.31.0, released 2020-01-22.)
180