Hacker Newsnew | past | comments | ask | show | jobs | submit | mikojan's commentslogin

I want the harness to use read freely but require confirmation for write.

It won‘t..

That's what Skills are for

:^)


0 tokens per command >>> Hundreds of tokens per command


No shit


"Probably"? I'd hit that a thousand times just to be sure.

Don't understand how one can experience anything but infinite dread when confronted with the effects of these models on the arts.

Maybe I am getting old. But I don't think so...


If I had to guess, I'd say that it's actually more of a young person thing to want to get rid of all AI. I've only ever seen older people wearing a shirt with an AI generated image on it.

I would absolutely push that button a thousand times as well.


I mean, there are some positive uses for the technology, some will likely save lives and advance the frontier in medicine and science. The ways it's able to automate research tasks is a pretty big deal. And, even though I know that, I think with the harm it's doing to our humanity with all this slop overwhelming everything (the web is now more slop than human, YouTube and every music streaming app soon will be), it's maybe not worth it. I don't know how to balance those two things. And, I don't know how you'd regulate it to make it safe, even if we had politicians anywhere who wanted to.


Hard to believe... This activity should certainly land you in a German prison?!


since its a .ch domain, i believe its in swiss. In germany we have our DSGVO (GDPR), and you can report it too. If a breach happen, you have to inform all your customers. if its a first time and you tried to your own best, the punishment is not that hard, but since these are medical infos they should have known better.

Lets really hope they learned from their mistakes


Switzerland is very liberal in terms of business-oriented regulations to the point that you could crate a new year party in a closed cellar without emergency exists, not to mention anti-fire installation and burn people alive there.


> I see the same thing repeated in various front end tooling too. They all claim to be _much_ faster than their counterpart.

>

> 9/10 whatever tooling you are using now will be perfectly fine

Are you working in frontend? On non-trivial webapps? Because this is entirely wrong in my experience. Performance issues are the #1 complaint of everyone on the frontend team. Be that in compiling, testing or (to a lesser extend) the actual app.


Worked on front end for years. Rarely ever hear people talking about performance issues. I was among the very few people who knew how to use the dev tools to investigate memory leak or heard of memlab.

Either the team I worked at was horrible, or you are from Google/Meta/Walmart where either everyone is smart or frondend performance is directly related to $$.


"performance is directly related to $$"

It is. Company size is moot. See https://wpostats.com for starters.


There are some really fast tools out there for compiling FE these days, and that's probably to what they refer. Testing is still a slog.


Uh, I've worked for a few years as a frontend dev, as in literal frontend dev - at that job my responsibility started at consuming and ended at feeding backend APIs, essentially.

From that I completely agree with your statement - however, you're not addressing the point he makes which kinda makes your statement completely unrelated to his point

99.99% of all performance issues in the frontend are caused by devs doing dumb shit at this point

The frameworks performance benefits are not going to meaningfully impact this issue anymore, hence no matter how performant yours is, that's still going to be their primary complaint across almost all complex rwcs

And the other issue is that we've decided that complex transpiling is the way to go in the frontend (typescript) - without that, all built time issues would magically go away too. But I guess that's another story.

It was a different story back when eg meteorjs was the default, but nowadays they're all fast enough to not be the source of the performance issues


Agreed. Optimistically let it resolve merge conflicts in an old complex branch. Looked fine at first but was utter slop upon further review. Duplication, wildly unnecessary complexity and all.


Dear god please let AI get forever stuck at this point because it would be so funny


Just view the "input cost" vs "output accuracy" graph.

It _is_ stuck at this point.

There's so much money involved no one wants to admit it out loud.

They have no path to the necessary exponential gains and no one is actually working on it.


Hilarious thing to say when we've just had some of the biggest leaps ever with Gemini 3 and Opus 4.5.


The greatest grift of all time.

I don’t mean the tech itself—-which is kind of useful. I mean the 99% of the value inflation of a kind of useful tool (if you know what you’re doing).


AI is not a bigger grift than crypto. Crypto produced basically nothing of value. If all model improvement stops today, Opus 4.5 with Claude Code is a huge leap in productivity building certain types of software.


I would disagree on the huge boost to productivity but it is a very useful tool.


Just one more new model bro the next one is AGI bro just give me a trillion dollars and I’ll build the datacenters and everything will be perfect bro I promise bro please


Even if it doesn't see any improvements beyond this point it wouldn't be a big deal. It's good enough for most programmers and any improvements are just a bonus.


The masters of mankind are yearning to replace expensive tech workers with this. With agentic versions of LLMs we are at a point now where they can (and should) certainly try and create a more hilarious world


GPT is the middleman.


Why Tailscale instead of plain wireguard?


probably because you just install it, then you log in and youre done. tailscale takes care of the rest. going through any more effort just so you can write some slop code is probably not worth it


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: