781
I think I have LLM burnout
I didn't expect to get so tired of reading LLM output.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,698 posts.
782
Turning a MacBook into a touchscreen with $1 of hardware (2018)
We turned a MacBook into a touchscreen using only $1 of hardware and a little bit of computer vision.
783
Emacs appearances in pop culture
Thank you for the support, this blog post got featured on the front page of Hacker News (YCombinator).
784
How I got over 300 Tor exit nodes removed
On Friday Oct 2, 09:35am, 333 infected exit nodes started a coordinated campaign to intercept SSH connections and gather as much unencrypted data as possible.
785
There is minimal downside to switching to open models
There was a time not too long ago when using Linux entailed some professional risk 1 . First there was compatibility: you may not have been able to render a Word document or PowerPoint correctly, and you might have had to trust Open Office’s export capability to render docs the way you wanted. There might have been…
786
Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK
I built a device to measure end-to-end input latency, then used it to find out what actually moves the needle.
787
Bug Blindness
I used to wonder why I see so many more bugs than most people. I easily observe hundreds to thousands of bugs per week and nothing seems to work , but most people I talk to don't see anything like this . For a long time, I thought this had something to do with how I use computers but, over time, I've realized that…
788
789
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 …
790
Websites Should Be Printable
I read a lot of printed papers these days. While I enjoy reading on a laptop as much as the next guy, marking up a printed document engages me better. Also, there's something about sitting with a whit…
791
Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
LM Studio 0.4.0 introduced llmster and the lms CLI. Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.
792
Sandboxels
Relax or experiment with over 500 materials in this falling sand simulator.
793
794
You can just say it
There is a weird collection of arguments for appraising the value of humans and their creative artifacts. It usually goes something like this: In the age of AI, we should still prefer humans in certain roles because AI could never perform the tasks required for that role. Or, a human can at least do it better. Or…
795
Will vibe coding end like the maker movement?
Is your vibe-coded app a Crapject or a Gift?
796
797
The best response to AI slop and online noise is from Robin Williams
There's a moment in the movie Good Will Hunting which perfectly summarizes all the problems with AI slop and online noise and infinite advice content. Sean (played by Robin Williams) is sitting next to Will (Matt Damon) on a bench in Boston Public Garden. I live here, so I know it well. The area
798
A shell colon does nothing. Use it anyway
I've written more shell scripts than I can count, but I still stumble upon tricks that honestly blow my mind far too often than I care to admit. Latest thing that blew my head clean off? The shell colon.
799
The changing goalposts of AGI and timelines
Based on its own charter, OpenAI should surrender the race
800
How to Exist
Here’s an experiment for a true daredevil. Sit there for a three minutes, following two rules:
801
GitHub Actions is slowly killing engineering teams
Why GitHub Actions is the Internet Explorer of CI, and why Buildkite offers a better path forward for teams that care about developer experience.
802
Download your favourite YouTube videos
Signal boosting Laura's post that you should absolutely download and archive the stuff that matters to you.
803
Overgrown, when plants invade your abandoned tabs
A fun little project that came out of a creative exercise around the word 'Overgrowth'.
804
Gas Town's agent patterns, design bottlenecks, and vibecoding at scale
On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code
805
AI Made Writing Code Easier. It Made Being an Engineer Harder
Writing code is easier than ever. Being a software engineer is harder than ever. The paradox nobody talks about, and what engineers and leaders should do.
806
When hardware goes end-of-life, companies need to open-source the software
Blog post by Marciano Planque: EOL
807
I built a vulnerable app and spent $1,500 seeing if LLMs could hack it
As a part of my work I do security research for various apps and websites. I wanted to see if LLMs could reproduce a common class of exploits I've found in multiple apps. So I built a deliberately vulnerable book review app and spent $1,500 finding out…
808
Go Concurrency Distilled
Interactive mini-book on concurrent programming in Go.
809
UK Government’s ‘AI Skills Hub’ was delivered by PwC for £4.1M
Or, as they like to call it, the 'AI Skills Hub'. Which was built by PwC because of course it was
810
U+237C ⍼ Is Azimuth
One year ago, on 28 February 2025, Wikipedia user Moyogo updated the page for Angzarr with a citation to the type foundry H. Berthold AG’s 1950 symbol catalogue listing ⍼ as Azimut, Richtungswinkel , or “azimuth”, “direction angle”. Mystery solved!