browsers offload inactive tabs from memory anyway, unless you’re actively switching among 15+ tabs, they won’t be using as much ram

My honest opinion is that it’s bad because a lot of people using LLMs have no standards and push the first thing that seems to work. Be mad at who’s at the driving wheel, not the car.

You absolutely can generate crap with agents/LLMs, and like a humans writing, the first draft will probably be subpar or maybe complete garbage. Every new session is a clean slate, that’s why putting effort in the documents guiding it is so important.

I don’t think there was a lot of people working on the rewrite. Most PRs are from bots. Original estimates for a manual rewrite were a small team working for a year or so, which puts total costs over $1M. Even doubling the token cost estimates, it was still cheaper than doing it manually by a factor of 2x-3x

I’ve seen plenty of code in my life, from humans and AI.

For the past year or so, these agents can code just fine most of the time, as long as they are given enough context (or have the tools to get it). Regardless of how many downvotes I get here, they really are capable of generating decent code. I’m sorry you couldn’t make it work yet.

It was higher sure, but anthropic also has some of the most expensive models out there. That cost could be 5x-10x less just by going with cheaper model providers (if one were to pay the API costs, not the case for bun).

bun 1.4 was released 3 weeks ago, btw

unironically, a better prompt does yield better results - shocking, I know

well, that depends entirely on your prompt/process, it can be done

fuck; I’m so used to dark patterns like these that whenever I read “cookie” my instincts flip and look for the less noticeable / most hidden buttons instead. It took me a few seconds to even realize this was a dark pattern.

Other common ones to be on the lookout:

• Filled out buttons that favor the company, while outlined buttons (or even just links) that favor the user;
• Toggles phrased as negatives, so “enabling” looks like “disabling” and vice-versa;
• Wording to disguise user intent: “Confirm choices” or “Save preferences” instead of “Reject cookies”, like above;
• Sneaking in optional checkboxes among mandatory ones at the end of a form;
• Small and low contrast elements to minimize important information that favors the user;
• Emotional manipulation: “this offer expires in X minutes”; “only Y left”.

yes, I get that and it’s a bad default, but not RCE like the post says

That does not allow remote code execution. An attacker still needs a vector like an SSH session to be able to control kitty. And at that point, if they already have a shell session, they don’t need kitty to do damage.

edit: giving access to other programs is not remote execution, but obviously not a good default.

yeah, unfortunately regulations have a bad habit to catch up with reality after the fact. By the time we actually have people in charge making better choices it’ll probably be late.

30 rockets a day? wtf

why can’t he just build bunkers, like reasonable billionaires

That doesn’t affect me, but you can’t eat your cake and have it too. I’d rather have open source content actually open and easy to access, but GitHub has an availability issue and they’re trying to address it, so I don’t see this as a hostile move.

I’m sure if codeberg was nearly as popular as github, they’d be forced to restrict some clones too. Their current load is unprecedented, even for their standards.

The problem with Codeberg now is that there is a spectrum of AI usage between manually coding and AI slop that Codeberg chooses to ignore with their new policy.

I get it that’s their platform and their choice, and at some point I even looked for ways to support them financially if that meant I could migrate all my repos from GitHub - I wouldn’t mind paying for my use, “vibe coded” or not - but an intransigent LLM ban creates uncertainty for many of my active projects, and I can’t consider them a viable alternative to GitHub anymore.

So sure, I’ll take 3h of GH actions downtime a month over a platform ban. I’m sure I’m not alone there.

You might be a few years behind. We have robots outpacing human performance in specific tasks using neural networks.

Also, LLMs can perform on tasks they weren’t explicitly trained for. This line is not as well defined as you make it sound.

as someone born in one, I think Florida might be worse.

If you have an SO like that, save yourself the drama and break up now.

systemctl list-unit-files --state=enabled to check everything enabled that you might want to disable

as for running as root, AFAIK all systemd services run as root, unless they’re defined at the user-level; but IME setting services at the user level usually means a more involved setup to make sure PATH and env vars are correct.

is backrooms a secret NSA project after the success of backdoors?

oh that’s actually a thing, neat