I posted a few months ago about vibe-coding an RSS reader. The mood on the internet seems to be that these apps are buggy and never get finished, so I figured it was worth posting an update. Another thousand commits later, Lion Reader supports every feature I care about, works reliably, has very good performance, and is open for public signups.
I’m part of a small Discord server and thought it would be funny to make a Geoguessr-style game where you get presented with a random interesting message from the server and have to guess when, where and by who it was posted.
Running Claude Code locally is annoying since you have to deal with permissions and agents interfering with each other (and you have to be at your computer), but running Claude Code on the web is annoying because the cloud environment is so limited.
What if we could run Claude Code for the web but on our machines? Through the magic of Claude Code writing Claude Code code, I made a local app for this.
Announcing Clawed Abode: A web app you can run on your own home computer which runs Claude Code without permission prompts in ephemeral containers, and with the ability to install packages, run containers, use caches, and access the GPU.
In the last few weeks, I’ve been playing around with the newest version of Claude Code, which wrote me a read-it-later service including RSS, email newsletters and an Android app.
Software engineering experience was useful, since I did plan out a lot of the high-level design and data model and sometimes push for simpler designs. Overall though, I mostly felt like a product manager trying to specify features as quickly as possible. While software engineering is more than coding, I’m starting to think Claude is already superhuman at this part.
One of my favorite AI papers is “Lets Think Dot By Dot”, which finds that LLMs can use meaningless filler tokens (like “”.) to improve their performance, but I was overestimating the implications until recently and I think other people might be too.
The paper finds that LLMs can be trained to use filler tokens to increase their ability to do parallel reasoning tasks. This has been compared to chain of thought, but CoT allows models to increase sequential reasoning, which is more powerful. I now think this paper should be taken as evidence against LLMs ability to perform long-term reasoning in secret.
