Nope, nobody can really do matter expert stuff reliably like that, the HN crowd is just devs, not general geniuses, let's not sugarcoat this.
You guys know the game tekken, right? Tekken 3 and 4 were before the vast majority of llm training feeds and it shows, there's a move sequence for Bryan, taunt into while standing 1, I've dabbled in this with programmable controllers , frame by frame recording, not a single llm model could explain how and why this works.
If it would understand the game mechanics, it's trivial, but it just does not understand.
Just because a dev can read and interpret an api documentation doesn't mean he is an expert or even remotely close to that.
Arguably, llm are "good" at programming. Where's the disruption in cpp hft ?
Yeah I've been doing this since even before you could run DS via claude code, it's damn near the same quality with plenty instances where claude had to eat a hat and a shoe and use DS corrections.
American folks really have a distorted sense of reality and few have their own mind, they listen to influencer noise and once self thinkers pick up the quality of things like DS, they will echo the statements.
Cool, schultz made the docu, but I've seen this thread before any doubts were raised by anyone, it's a hilarious read by people who understand the topic and they called bs before any exposure.
Just keep it simple, quoting verbatim
The board of directors looks more like a team to negotiate peace with Iran rather than an actual biotech board
As a point of reference, I tried an experiment with Claude Code and the latest Opus the other day. It was work for my company, so this was using API tokens and not the individual user plans that have non-commercial terms.
A simple task, migrating a typical password reset flow as part of updating a long-lived web application from legacy libraries and software architecture to modern equivalents, apparently cost roughly the same as 2 months of Pro subscription, over the equivalent of about half a working day in wall time.
It produced code of decent quality at a small scale, but it wasn’t always on point architecturally. It also had a tendency to drift off topic and try to tangle up other changes it decided should be made with the main change we were supposed to be working towards. So even for a routine task, based on a plan developed using the harness first and with the agents working under close supervision, a near-SOTA model is still producing quality on par with a decent mid-level developer but substandard for anyone senior+ in this case.
Moreover, based on a direct comparison with other migration tasks of similar complexity that I’d already done by hand, it was actually a bit slower overall to work this way. I had to babysit Claude throughout and review everything it proposed carefully, both to avoid subtle errors (it would have made several) and to prevent drifting off track. I also had to spend a significant amount of time cleaning up its final output to an acceptable standard after the session. Those two overheads more than cancelled out the much faster code generation an LLM offers under favourable conditions.
So for now, I remain sceptical about these high multiples of improved productivity that I keep seeing claimed online from people who are apparently writing almost everything using AIs now. I could certainly have achieved a multiple of my normal productivity by YOLOing everything without reviewing it in detail and then accepting the output code without tidying anything up. However, I doubt this codebase would still have been good enough for normal human developers to work on it reasonably after even 10 or 20 AI-led sessions like that. The architecture would have degraded significantly and the test suite would have been large and largely pointless. And again, this wasn’t rocket science in this experiment, it was completely unremarkable maintenance of a relatively small and simple web application.
Definitely, according to my omp stats I spent the equivalent of $650 opus 5.5 tokens at api price, this model isn't even a month old, I'm exclusively using the $20 plan and I'm not a power user at all: no backround loop, no automated anything, just using it for development and I stay in the loop the whole time
Yes. Hundreds of dollars per day is easy to burn with Opus if you pay the API rates.
And now if you get the task done faster with the same quality. And the cost is 80 cents, considering DeepSeek and your own server starts to starts to be relevant...
How can you say react isn't bloated it requires a full download on first website visit, web components are browser native, not saying they're better, but to say react is not bloated is an affront , there was a time where people were carefully deciding on whether or not to include jquery.
If you are referring to how SSR pages need to download the serialised page "props" and not just the html+js then good news! Solid 2.0 is about to solve this.
If you are referring to having to download react itself then you have to download the WebComponents code too.
Actually with smart use of forms and links you could make a js free react page (using forms to submit state changes) more easily than for WebComponents
Everyone was slurping the chat jeopardy and anthropic kool aide here, I was using DS before it became available via cli, and it was evident for who's not blind how good it is.
Tune has changed finally, but damn, for HN , embarrassingly slow, has to be said
Besides, which government do you want to run .com domains
reply