9dev

If only there was an exhaustive explanation offered answering this exact question after the quizz.

> confidently running wrong commands, answering something without looking it up, getting stuck on long scripts and not self-correcting all absolutely still happen, so the statement isn't incorrect.

That is just my point though; these things still do happen, but much, much, much fewer than they used to, and this changes massively every month - both due to improvements in the models themselves, but also experience gained from operating them.

Forming an opinion on using agents for software work once, and then treating your experience as the status quo months later thus leads to wrong conclusions. If you give a model a way to evaluate its work in a short, closed feedback loop, you can orchestrate it to build correct systems pretty easily now. That definitely wasn't true even just three months ago.

If, however, you do not actually use this technology regularly, you will not be able to achieve good results, which objectively makes sense and wouldn't be different for any other skill either.

And thus, StackerNews was born.

I really also meant nested in discussions on other submissions, not just Ask HN - I have found amazing gems hidden downthread of posts through the years, sometimes from internet legends or high-profile maintainers directly.

If I had time, I’d do HackerOverflow - all threads where HN users help answer technical questions and help debugging!

It matters the same way saying “solar panels are super expensive” has been historically true not too long ago, but prices have fallen so rapidly it’s simply no longer a correct statement - even if you will occasionally come across an overpriced offer here and there.

A diverse Committee that makes its own decisions, and politicians abstain from influencing it. Because it is intended to be independent, and people see value in that, so they honour it. Nobody needs from the outside to have a say, because politics and the committee trust each other to do the right thing. It's alien, I know.

There's usually a little more dignity involved, with people generally at least trying to be discreet.

I can assure you that as a fellow European, both this amazing jab at the Clown in Chief and the beautiful vistas have renewed my interest in travelling to Norway as soon as I can, so I'm pretty sure it will pay off!

[flagged]

You know, there’s a world out there beyond the prison. It has no locks and no fences. You can just choose to go outside, right now; go for a hike, see some trees, watch a bird. There is nothing stopping you from never visiting the prison or the bar ever again.

Product Engineer would be my term

I think it is: From my personal experience, it's the orgs that fail much more so than the technology. If you have a few capable engineers with AI that are able to think strategically and prod the agents from the right angle, you can move ridiculously fast.

Code quality improves month by month, and by now I rarely have complaints in PR reviews, even if I read through them manually, line by line. For the most part, it's how I would write it myself, only that I would have been slower, and not as motivated to test it so thoroughly.

The key is IMHO giving the agents a way to verify their results in a feedback loop as short as possible, along with few instructions for the important guardrails, and a way to organise efficiently (a ledger, a GitHub repository with issues, Linear, Jira, whatever.) With that, you can tend to 3-5 parallel sessions to avoid waiting, and actually get stuff done fast.

It’s the NY Post. Did anyone really expect serious journalism..?

Are you sure this isn’t already happening?

These kinds of replies always astound me. Like, I have a better use for my attention and token limit than building and fiddling with my custom agent harness?

And that’s exactly where it starts to get murky, because this isn’t a clear gradient after all but a matrix of different qualities for different tasks. Reasoning effort levels are one factor here, but the whole speed vs. Quality topic is another.

Go to a random coffee shop that allows people to work at the tables, and you’ll find a few developers with MacBooks there pretty soon. They will be connected to the local hotspot, which either has no password at all, or WPA2 with the password written on a billboard behind the counter. Spin up an evil twin, then wait for the connections to roll in.

I don’t think that’s either targeted or unlikely?

…and yet it doesn't help at all if a laptop sees an AP with strong signal in its vicinity and connects to that instead of the meticulously configured AP that sits behind the counter with a slightly weaker signal.

That page is an insult to their customers. So what, if I want to be protected from a security issue you acknowledge, I'll need to make modifications to my system configuration?

Yes. The entire internet is US-shaped. From social networks applying ridiculous puritan beliefs globally to the madness that is the TLD system, DMCA, the CLOUD act… all the way to the NSA spying on non-US citizens to protect themselves.

A Puerto-Rican crypto bro wouldn’t have a career without the USA exerting their will and regulations onto the rest of the world.

It’s so funny how Americans seem to assume it’s the natural order of things that the whole world has to comply with American regulation, but lo and behold if the EU dares to have laws of its own!

Don’t make this a Both-sides thing please. There’s a clear difference between those who are working hard to void any environmental protection we have, and those who oppose that.

that... is a good point.

I do the same. Bookmarks are a case of “out of sight, out of mind”, whereas I come across open tabs eventually. They are like physical cues to remind me of things, akin to leaving the trash bag in front of the door so you can’t forget to take it when you leave.

I'd suggest also adding blank modules without a switch on them for empty space on the keyboard (for example around arrow keys), that would still provide the interconnect to adjacent keys. Cool project.

Double the fine every day the entity in question is in violation. They will stop rather soon.

That’s two things they’ve got in common!

Ask any neurologist near you, and they will readily confirm how Trump exhibits all signs of dementia and mental decline on national TV every single day.

I take it you’re a software engineer and have never seen even a single percent of all things people use Office for.