Viewing profile — boron1006

It’s a good question and I don’t doubt they’re useful. But I mean they’re not good enough to do the things I need them to. Not enough that any difference can be chalked up to “tast…

I don’t like the term taste, but the problem that I have is that LLMs don’t seem to work “good enough”. They seem to be able to solve the immediate problem, but stacking this on th…

[dead]

This is true but also false. In my experience (scientific programming) AI is a giant multiplier for people with specialized knowledge. But it’s also a giant devaluer for that same …

What I’m saying is that it often uses metaphors in ways that are subtly wrong or don’t make any sense.

Or in a way, nothing at all.

I think that’s just a fundamental tradeoff though. Being able to run Jupyter cells independently is a feature until it’s not. I’d say for most of my one-off work, it’s fine. But fo…

I just dont think LLMs are very good at judging importance or summarizing code. I tried experimenting with what is ultimately a treesitter based approach - https://github.com/0x007…

I guess I’m thinking a lot of companies seem to be getting Claude code subscriptions. It usually takes some time and effort for an org to switch away from one solution. In the mean…

I think anthropic with its enterprise strategy and google with its integration in everything have a bit of a moat. But I switched from ChatGPT to Claude 3 months ago because my acc…

Yeah I hope the links are helpful

I posted about my project below - https://github.com/0x007BA7/codebook But maybe you should checkout the tools it’s based on, sem - https://github.com/Ataraxy-Labs/sem and ultimate…

Codebook - https://github.com/0x007BA7/codebook It’s a better code reader built on top of sem (treesitter). I’m getting a lot of massive PRs at work now, and this has helped a lot …

This has always been the fun part of programming to me. I know most people hate it, but I really don’t mind being on-call (ok I hate being woken up) and fixing weird bugs that user…

I do think people are seeing useful results, but it’s at least several orders of magnitude less than what is claimed. My metric is: how much code that I create today do I depend on…

More generally, I think it’s more specialized knowledge. If you have particularly specific knowledge in pretty much any domain, combining that with AI can lead to huge gains.

> Sounds terrible, but is it? Yes > It incentivises high-impact research It incentivizes work that sounds impressive to laymen. Actual work tends to be technical and might not soun…

It doesn’t apply to what this repo is doing. Also the 70 odd single author preprints seems to suggest the author is in some deep AI psychosis: https://www.researchgate.net/profile/…

Well the √t stuff looks like nonsense or way overblown, existing tools already do similar things, there’s pretty much a single commit with no follow up commits etc etc.

Lots of bad smells in this repo.

Tech “decision makers” are feckless lemmings. If the trends tomorrow change, then their decisions will change.

At least where I am we can’t and shouldn’t know all the requirements of a project beforehand^. Every project is an iterative learning process between the users, product and enginee…

At least for some people I know it’s not necessarily because there’s pressure from leadership, but because it’s funny that the org spends like $15,000/mo writing HP fanfic or whate…

> Claude is a phd level mathematician , I am not I’m going to guess that this is Gell-Mann amnesia more than anything, and it’s going to get a lot of organizations into a lot of we…