Viewing profile — munro

If you bounce off the wall at the start, and RNG gods look down on you, you're lined up to go through castle on first shot. Then knock it through castle, and lined up for 3rd final…

Lately I just have Claude build most things in Rust, it's really amazing. I tried Go, but I found it wasn't as good--Rust really does to me feel like Python. That said, it still st…

Awesome haha, they look so shocked when you send a message, and then I get embarrassed and spin again

> Rule 5. Data dominates. If you've chosen the right data structures and organized things well, the algorithms will almost always be self-evident. Data structures, not algorithms, …

ChatGPT needs to catch up hard, for me their model is unusable and I cancelled my subscription 5-6 months ago, so to me this post is hot air. I need to see results, going back to t…

>=99% accuracy wtf?!? I was initially excited until i saw that, because it would reveal some sort of required local min capacity, and then further revelation that this was all vibe…

I was looking at using this on an LTO tape library, it seems the only resiliency is through replication, but this was my main concern with this project, what happens with HW goes b…

seriously cool, i just did something similar with quantiles for even bucketizing on arb key data types (still needs ord tho)

just use a calendar event, it's more robust, and gives you the same feeling of 'oh yea...'

I had built an agent with LangGraph a 9 months ago--now seems React agents are in LangChain. Over all pretty happy with that, I just don't use any of the dumb stuff like embedding/…

I built an ML classifier for product categories way back, as I added more classes/product types, individual class PR metrics improved--I kept adding more and more until I ended up …

Amazing, some people are so enamored with LLMs who use them for soft outcomes, and disagree with me when I say be careful they're not perfect -- this is such a great non technical …

I'm more looking at the problem more like code https://bbycroft.net/llm My immediate thought is when the model responds "Oh I'm thinking about X"... that X isn't from the input, it…

I love the irony of the site showing a MASSIVE banner with a huge green "Download Extension for Mac (Free)" button. This thing is 280px tall! I clicked it for shits and giggles and…

I wish they dug into how they generated the vector, my first thought is: they're injecting the token in a convoluted way. {ur thinking about dogs} - {ur thinking about people} = do…

But what if `ty` was also eventually merged into `uv` as well? 8-) That's probably the vision, given all from astral.sh, but `ty` isn't ready yet.

Link to paper here https://arxiv.org/pdf/2506.21734 Still reading, but the benchmarks for ARC-AGI-1, ARC-AGI-2, Sudoku-Extreme (9x9), and Maze-Hard (30x30) look impressive.

was a bit hard for me to find, but here's a video of the trackball being used: https://www.youtube.com/watch?v=RCXgPqlpZeM

That's sort of how I felt about things before, but the reality I believe is we wouldn't have uv if they 'just contributed to poetry'.

No model is perfect, but some are useful. Their "baseline LTV" looks at the sum of listings on their platform (plus other features), then tries to forecast the next 365 days — so t…

Here's an interesting write up on various algorithms & different epsilon greedy % values. https://github.com/raffg/multi_armed_bandit It shows 10% exploration performs the best, ve…

Wow, this is cool-- first time I've seen generating well formed output has been made easy, the use of Pydantic is clever/easy... Which has lead me to the prior art: using same Pyda…

Lots of amazing ideas here! One more that would be great is 'sandboxing' if a program can use network/filesystem/etc, then I would feel safe to run any random scrap if I knew I wou…

> Haha used to be 1PB, stored completely on Google Drive (they had unlimited), but then they cut me off so I cut down to 300TB and switched to self hosting at a data warehouse. > N…