maCDzP

I did Nand2Tetris and then I understod why I need to vectorize. You get a view from nand-gate to software and get to see all the interfaces. Its a wonderful course.

During uni I only took a Java class. During the exam I had to turn in hand written code. I guess that would work today.

This. I managed to run Gemma 4 31B on AMD MI250X for CPT and SFT with Claude. And I have ZERO experience and knowledge of how to train and work with GPU:s. The training didn’t go where I wanted. But I manage to direct the AI to build it. It’s crazy. I am excited and scared.

I run Claude Code on my VPS and do /rc to run from my mobile. It’s really handy.

I train on AMD MI250X and managed to get Gemma 4 31B to work - but it took a lot of work on the software side.

I have tried that and it works well for me. I can also recommend using a Visual Studio plugin called Markco that lets you comment a markdown file. It’s resembles words commenting feature. I use it to comment LLM generated markdown.

I have a ML project. I usually set up a team of agents, where I have a leader, archivist, research assistant, researcher, developer and tester. The team generates hypothesis based on papers, test it, and iterate over that. Everything is documented using a lab notebook. It burns tokens but I have found some promising strategies that I am testing.

Thank you! Didn’t know that existed.

Nice, I am going to this for Swedish law! Any suggestions on how one can model parliament voting when a law passes using GitHub? Or all the work that preceded a law, that’s like a feature request or a bug report.

Do you have any good resources for what you are describing?

Now with AI I wonder if it’s possible to just let agents build a perfect emulation of the game. It reminds me of fuzzers. You let the agent go loose on the game and it brute forces every possible state. Then recreates the code. It’s very inefficient- but it probably works.

I dunno. I just let Claude build a python script that calls Claude code though subprocess.run().

I recently made a sort of Autoresearch with that approach. The script calls Claude Code to create a hyphotesis, then code based on that, evaluate- rinse and repeat. I am still trying to figure out if I am actually on to something or just burning tokens. Jury is still out.

Has anyone tried to set up a container and let prompt Claude to escape and se what happens? And maybe set some sort of autoresearch thing to help it not get stuck in a loop.

I want this the other way around as a plugin in Chrome. So I can easily spot the bullshit. And I would prefer that it translated LinkedIn to something salty, maybe pirate speak?

I really want a DeathClaw product.

I bought magnetic self adhesive tape and mounted in on my fridge. Now it’s the family calendar. So nice.

y7u8888888ftrg34BC Alright, let me decode this masterpiece of cryptic genius...

Those three dots made me smirk.

I use CLAUDE.md to describe the project. I use Claude to help write the spec. Then I let it run. When the context gets too crammed, I have it build SKILLS.md. I’ll probably have it rewrite CLAUDE.md after a while. Then it will write tests, deployment scripts, commit messages. Yeah, everything.

Maybe someone knows law can answer this. Is it a crime to ”unredact” files in the US? You probably know that the information is classified since you are putting in the work. Where I live I believe it’s a crime if you share information that is classified even if it’s leaked. So I would not publicly brag about this online.

I wonder if there are any traces of the text inte file. Seems like a fun forensics exercise.

I listened to a yogi talking about mindfulness. He mentioned a session he had with a woman where they where working on the concept of flow. The woman had an experience of flow when she was bitten by a shark. She said that if she could make a drink that would create that feeling she would addicted the world. I think about that sometimes.

I used to think stoicism was great. But now I think that it’s not so great. In retrospect I should have focused on changing my situation in stead of learning to live with it. Compared to Aurelius - I am not living around 0 bc - in today’s world I can change a lot of things.

I let my curiosity set the depth.

Who was it that used it 24/7? THIS IS WHY WE CAN’T HAVE NICE THINGS!

This looks cool. So this is extending the tech from Trimble/Topcon with LiDAR in order to have a fully autonomous excavator?

How would I handle faulty geotechnical surveys? It has happened several times that the trench caved in and the operator saved a persons life.

Does anyone here have some tips how to ”opt out” from this?

I work in this field - below are my two cents.

I have a hard time seeing that this approach would work. The environment is very messy and there are many field tested methods that don't involve digging up the whole street. One example of such a method is pipe bursting.

There have been loads of research in using AI (neural nets etc.) to find and predict pipe bursts. But I believe simple linear regression is enough since my gut is telling me age and material is a good predictor.

Where I live there is a strong seasonality because the ground freezes over and during thawing we have a lot of leaks. This is a local issue since it depends on both weather and geological environment.

This is neat, do I have to hook up an keyboard to my computer. If so, any suggestions?

Glad to hear that I am not the only one! My prompt had more of a ”actor director” flavor. It went:

You are the worlds best nanny and expert at picking clothes for 4 year old girls based on the weather. Your answer is concise and to the point. Below is today’s forecast:

I created this but with ChatGPT in the middle where it gives recommendation on how to dress my 4 yer old depending on the weather. It messages my families telegram channel.