rolisz

Can you give some pointers around this? I'd gladly help with a PR for this, but if you have anything docs/ideas around this it would be helpful.

Do you have non24 sleep disorder? Eliezer Yudkowsky has it and @exfatloss150 . Both have written about how they manage it.

Not quite. Model is extremely important in the quality of results. Harness can also influence things.

With Claude Code Ultrathink, I used 3 million tokens in 20 minutes. At API prices, that would be around 30$. So 90$/h. Model cost is not that much lower.

If it's anything like Claude Ultracode, it burns 3 million tokens in half an hour with a single prompt.

Armin is very nuanced and balanced. He spells out clearly in the blog post that bad parts of AI

About stress: how's your HRV? Look into sympathetic and parasympathetic nervous system, vagus nerve and it's relation to HRV. It gives you a more objective way to measure stress.

In particular, Garmin smartwatches have a very good measurement and intepretation with their "stress" and "body battery" features.

I'm interested in trying something similar. I was thinking to do this for my OpenClaw agent.

About Owain Evans work: I think he did SFT. On Twitter someone was saying that RL is not as susceptible to what he showed. I'd like to try that

if there are no customers they’re not costing you more money, unlike your computer which you are using for training

So are you using the computers or not? I'd argue that if you're using them for training, then it's not wasted capacity. And if you're not using them, then you can turn them off, so you're not sucking up energy.

Welcome to alternative health :))) there are many functional doctors, and others who perform this kind of stuff.

For example Organic Acids in Urine Test gives you some 70-80 metabolic markers, which some folks interpret. There's no large scale RCTs or studies on this, so it's a bit dubious. But I did one and the practitioner correctly read the leaves to suggest some things that were missing and which helped me (glutathione and B1).

Water fasting is used to differentiate from dry fasting, where you don't even drink water.

So Douglas Adams was right and the Earth is a computer created to calculate the ultimate question?

Opus 4.7 starts to try to shut down conversations if you are rude to it (it's easier to do this via API, look up what @repligate is doing).

And unprompted messaging: OpenClaw can message you unprompted (yes, there's a cronjob behind it, but the instructions matter and it won't always message you, only when there's something relevant).

Linux sucks in a way that is more controllable by me. I have run Arch Linux as my daily driver for 4-5 years. But I can't on a MacBook, which has the nicest hardware

MacOS sucks. I can't wait for the day Asahi Linux is good enough so that I can bail on it.

Safari, a web browser, randomly stops being able to connect to the Internet (other apps can).

@op: I tried BoringBar, I like it, but I run into a weird bug: I have two external monitors for my MacBook. BoringBar on the MBP display is fine, but on external screen 1 it shows the apps from screen 2 and vice versa.

I couldn't find your email on the site or in the app.

Coding is solved, but problems with code is not yet solved.

Sent this I a friend. Their reply:

Is it a bad sign that I am only skimming diagonally the AI summary of an article called "some things just take time" because it feels like I already know the idea?

I think they bought the books after they were caught that they pirated the books and lost that case (because they pirated, not because of copyright).

Well didn't they? From the Epstein files, it looks like "all" the elite is involved....

https://rolisz.ro my personal site https://rolisz.com my freelancer site

I've been using Claude code daily almost since it came out. Codex weekly. Tried out Gemini, GitHub copilot cli, AMP, Pi.

None of them ever even tried to delete any files outside of project directory.

So I think they're doing better than me at "accidental file deletion".

With Tailwind, wasn't the problem that much fewer people visited the documentation, which showed ads? The LLMs still used Tailwind

So, it's a personal pet project, I've thrown in everything and the kitchen sink. There's a telegram integration so I can submit entries via telegram, there's a chatbot integration so that I can "talk to my entries" and ask questions about what I did when). It imports weather data, Garmin data, and so on.

So yes, it's around 100k lines of code (Python, HTML, JS and CSS).

I can do that (via something like VibeTunnel), but usually I just use the Claude Code web/mobile app.

I can't convince my wife to let my kids keep the big cardboard box, even though they love it!

Ehrm, I beg to differ. My 4 year old daughter has recently also started loving to draw. But, she pretty much refuses to let go of her masterpieces, at least we conviced her to store them in a shoebox, so they're not spread all over the house. And the pencils... Well, I've been picking up an awful lot of pencils from all over the house.

So I'm not sure I agree with the "lowest clean up time", even though I'm really glad she's picked this up as a "hobby".

Not grandparent, but I'm in the same boat. I've been dreaming for almost 10 years of building a sort of digital bullet journal. I had some feeble attempts to start, but never got to the point where I could actually use it. Last year I started again, heavily LLM assisted. After 1-2 weeks (this was before agents), I had something usable, from which I could benefit, which wanted to make me improve it more, which made me want to use it more.

By now it's grown to 100k lines of code. I've not read all of them, but I do have a high level overview of the app, I've done several refactorings to keep it maintainable.

This would not have happened without AI agents. I don't have the time, period. With AI agents, I can kickoff a task while I'm going to the park with my kids. Instead of scrolling HN, I look every now and then to what the agent is doing.

Yes, it's a risk if you don't guide it well, but you can also manage it pretty ok.

I have a side project that I started in January 2024. Initially, used Github Copilot autocompletions heavily. This year I started using CLI agents (mostly Claude, but others too) to do more stuff. I got to around 100k LoC (sure, it's not enterprise scale, but for a personal project it's pretty big), but I'd argue it's maintainable, it's split into 10 Django apps, that are each pretty self contained, I've done several refactors on it (using AI agents) to make it more maintainable.

You're assuming that different models need the same stuff in AGENTS.md

In my experience, to get the best performance out of different models, they need slightly different prompting.