Viewing profile — f0e4c2f7

Lots of services have no desire to ever expose an API. This approach lets you step right over that. If an API is exposed you can just have the LLM write something against that.

Ha! This is great. I've been waiting for someone to make this. Giving an LLM a computer makes it way more powerful, giving it a kubernetes cluster should extend that power much fur…

I don't like the premise of this game. If you're autistic, don't mask. Live authentically as yourself and find people who love you for who you are. You'll annoy the hell out of som…

This looks cool and I wish you luck but I'd probably never use something closed source for this. Been on the lookout for an open source version but they all seem kind of unessecari…

Front page of HN. Funny to imagine thousands of people sitting in the office crossing their eyes at their computer screen right now.

There is a funny parallel I see with Kubernetes that I also saw a lot with Linux in the early years. There are thousands of packages and tools you can install on Linux (think phpmy…

Sounds like management and mentoring might be a satisfying diversion at this point in your life.

For sure. It's been amazing honestly and I feel like it has really accelerated my learning. Enough that I'm trying to get really serious about making the most out of this new lever…

Building using LFS has been on my list of "I really should probably do that just to learn" for about 20 years now. I'll get around to it! This year I'm finally learning Lisp (and r…

Really cool idea. Novel, I imagine a lot of people would play this. I would suggest a social media campaign with short form videos. Seems like something that has the potential to g…

There is one clear answer in my opinion: There is a secondary market for OpenAI stock. It's not a public market so nobody knows how much you're making if you sell, but if you look …

I'm a big fan of the reading list and structure of teachyourselfcs.com

Fortunately big tech jobs are available in EU too. Highest salaries might trickier without moving to US, shouldn't be too hard to transfer to US once you get a job at one if you wa…

This is fairly straightforward imo. Most money is in big tech. Look at levels.fyi to get an idea of the roadmap. Big tech hires mostly off leetcodes. There are other factors too. Y…

I'm not sure why but it seems like most of the high quality AI content is on twitter. On average seems to be around ~4 months ahead of HN on AI dev approaches. I would suggest foll…

There have been some papers showing that RLHF makes models more palletable to use but reduces performance on evals and in other various ways. I couldn't find the one I was looking …

This is a bit of a Zen thing you're describing. A lot of different approaches and theories on getting to the same thing here I would say. It's hard to think of specific advice here…

This book is so good. It's about building early computers but it feels just like tech does today in the way it's described. Which make it feel like this bigger context you're readi…

Currently listening to this series of interviews about Neuralink: https://www.youtube.com/watch?v=Kbk9BiPhm7o

Would be interested to hear the experiences of someone who has used this.

When I was a kid there was this new thing that came out called Wikipedia. I couldn't convince anyone it was useful though because they pointed out it was wrong sometimes. Eventuall…

This is an extremely good insight and piece of advice. Already we're starting to see what looks very similar to a "frontend" and "backend" kind of development model similar to the …

Is there a way to try this yet?

Lately I've been experimenting with using TDD approaches for LLM assisted coding. There is a little bit on YouTube and some research papers on this topic. But most of it relates to…

Exa is trying to do this. I've found some sort of interesting stuff this way but it honestly doesn't feel quite good enough yet to me. https://exa.ai/search?c=all