Viewing profile — blixt

It would seem like GitHub is in a precarious situation. We have many agents per employee working in parallel pushing way more commits than was humanly possible before AI, triggerin…

Fun data sheet! I was curious about most steps per part and it seems to be TROTTEN[1] at 1.07 steps per part (excluding some other products like a toilet brush with 1 part but the …

Yeah the UX doesn't seem great, though I do think in general the AskQuestion tool is very awkward when it gets used in a very long running process (I personally use Claude to run r…

Then I apologize, it seemed to me you wrote that part, but I guess I was reading Claude output.

So much attribution to malintent here, but most likely they're trying to build a product with the features that they themselves would use, and from my own experience it's very frus…

The biggest performance bomb you can have in your code is a loop that does something like for (...) { el.style.height = `${something}px`; whatever.value = el.style.offsetHeight; } …

I think I can see how dynamic data types make sense (eg flat key/value store), but my question would be: What is least surprising? That INTEGER implicity accepts 'hello world' with…

I tried running this for some market research for my startup and it did a pretty nice job. It didn't necessarily find any obscure data, and it seemed to rely on older data than wha…

JWTs are fine, seems a bit sensationalist title... Some nice topics to talk about instead: - When to use an encrypted value (and symmetric or asymmetric), vs. a random (but secret)…

In short, it lets you switch between all your Claude accounts seamlessly and will automatically pick the one with the most usage left. I've been using the c, cw, and cr shortcuts f…

If this shows itself to be highly useful as a concept, then I would perhaps avoid reinventing the wheel on the file format side of things, and just standardize what we already have…

I always find the minimizing view of consciousness a bit uninspiring. Like we need to be unique. I've yet to find a reason why it couldn't be the opposite, way more things are cons…

Yeah this can go many ways but there's a world where OpenAI doesn't sell direct model access for the same reasons Cloudflare doesn't sell direct hardware access.

I started getting into webdev using PHP almost 30 years ago. So I'm probably biased. But when you're developing on just one machine in one language and you can do most of the stuff…

Releases keep shifting from API forward to product forward, with API now lagging behind proprietary product surface and special partnerships. I'd not be surprised if this is the ye…

Isn't it pretty common for the smaller models to release a little while after the bigger ones, for all the big model providers?

I made this offline pocket vibe coder using Gemma 4 (works offline once model is downloaded) on an iPhone. It can technically run the 4B model but it will default to 2B because of …

Since AI became capable of long-running sessions with tool calls, one VM per AI as a service became very lucrative. But I do think a large amount of these can indeed run in the bro…

I’ve been building on an opinionated provider-agnostic library in Go[1] for a year now and it’s nice to see standardization around the format given how much variety there is betwee…

I've gotten to a point where my workflow YAML files are mostly `mise` tool calls (because it handles versioning of all tooling and has cache support) and webhooks, and still it is …

If the immediate next token probabilities are flat, that would mean the LLM is not able to predict the next token with any certainty. This might happen if an LLM is thrown off by o…

I went exploring whether using LLM tokens as the individual "digits" of random ids would let you get more randomness for the same number of tokens, and the answer is yes. Using the…