Viewing profile — sebmellen

Thanks for the attempt, but this is really a non-answer, which makes me think you have not worked with the kind of large, well-encumbered codebases / business problems that I seem …

Whoever is paying to spam this thread with useless AI comments should be banned from HN. It’s ridiculous.

Yes I agree with this. It’s all a matter of taste and interpretation at the end of the day. YAGNI has been useful for me in stopping the development of truly complex featureful wor…

I'm extremely surprised that Wyoming is more remote than Alaska! I wouldn't think Alaska has that many back-country roads running through it. Edit: they have another page describin…

I didn't realize you were the author. Super cool! I'll be trying it out. I do like the grug-brain approach of keeping things extremely simple and easy to reason about. One thing th…

Dude, Australia is like 95% sand and nothingness with Alice Springs in the middle. Where is your bullet train between Perth and Darwin and Melbourne? Boo! I jest, but not completel…

Do you use smol? How do you find it compares to other harnesses for things like MCP connections? I’m tempted to use it since I’m a fan of the philosophy.

All death is a bit strange.

I met Stephen in 2023 at some MIT AI conference. He was the kindest, most grandfatherly person. I was expecting to meet a relatively pontifical person given some of his work, but h…

So do half the comments on this launch post!

Yikes. Hello, Claudebot.

At the risk of replicating the classic Dropbox post (why would you need this when you could just use rsync?)… I have a dev box with 96 GB of RAM, 2x4 TB NVMe drives, and an unbelie…

Ahmed, are you an OpenClaw agent, or are you a human sitting there and copying each comment into Claude so you can have Claude reply while pretending it’s you? I can’t decide which…

This is truly some of the most beautiful writing I’ve ever encountered. Thank you for posting it.

Take a look at sun protective gear like Coolibar. It’s actually very pleasant to wear even in summer.

Very interesting, I’d never heard of Oban before, and that’s after a fair amount of research into background job queueing systems. Thanks for posting!

How do you prompt your diffusion models? I see that you are a founder in this space :)

This may help people: > Mary is 24 years old. She is twice as old as Ann was (12) when Mary was as old (18) as Ann is now (18). How old is Ann? So 6 years ago, Mary was 18, and Ann…

Friendly feedback: write in your native language and use https://deepl.com to translate. I am fluent in both German and English. I find Deepl does a much better job at capturing th…

I grind my teeth when I see it. It's so pervasive that I worry I'll pick up the same ticks by reading so much Claudeslop.

Hey, thanks for the comment! That's fair. The commitment/timestamping part is essentially the same idea. But try to think of prove-yourself like a framework around an anchoring ser…

Really cool. Makes me wonder where the most remote point in the contiguous U.S. is by this metric.

I built my first startup around an optimistic but extremely naive idea: if you get scientists to timestamp their work on a blockchain, and then couple that timestamp with a protect…