weavie

How long until adverts are injected into LLMs?

To be fair, that comment is by Boris Cherny, the guy who developed Claude Code. You have to give him a bit of slack for wanting to use his tool for literally everything.

I think a lot of people pay their phones off with a contract over several years.

Signing up for a new phone contract, you start looking at a $600 phone. Thats $25 a month plus $15 for your calls and data, so $40 a month. Then you see the next phone next to it thats only $1200, it's so much better, and you're only paying $65 a month for it.

And then they flash this one in front of you, only $67 a month (just ignore the fact it's now over 3 years instead of 2)! 5 minutes later, you are in.

How much of this is just down to your mail server being randomly assigned an IP address with dubious history or not?

I have ad blockers everywhere apart from the instagram app. I have bought a ton of stuff off the ads on there. I'm not proud, but have to admit I am powerless against them. Underwear, t-shirts, soap, online courses I have never used, I am a sucker, which is why I need these ad blockers.

I get an occasional request from a friend who is trying to build a following to interact with their posts to boost their visibility. I'll go through, like a few then sit around for a while desperately trying to think of something non-generic to say in a comment, fail to think of anything and just add an "I agree" comment.

Probably https://arstechnica.com/ai/2026/06/pokemon-go-players-unwitt...

It's amazing the things you learn here..

What kind of ads would you expect to see? "Hey, you're asking a lot of questions about Postgres lately. Have you considered moving to Oracle?"

The reason you've had more bad results than good is because you haven't fully learned how to use LLMs yet. They are not as simple as they first appear. I think a lot of people think using a coding agent is just a case of firing it up and telling it what to do and expecting to get it right first time. When it doesn't they just think it's no good and like you abandon the effort.

The reason a technical interviewer will be asking this question is because they want to see how you adapt to using new technologies, LLMs being one of the most disruptive technology that has hit the tech industry since at least the internet. You will likely be expected to use LLMs and they will want to know that you are someone who truly understands the capabilities of them - upsides and downsides, where to use them, what guardrails you need to put in place.

I'd encourage you to revisit the re-factoring task you worked on. Work out why it didn't work, work out what didn't work about it and if you have the chance try again, but use different techniques, there's a lot of conversations going on about what people find working and not working - try to join that conversation. Try to document what you learn. Then in the interview discuss these rather than just saying you gave up. The interviewer isn't going to check up on how successful your project was, they just want to know how you think and how you approach problems.

> I also started CPAP recently

A proper nights sleep is massive! I'd put 99% down to this..

Is this one of those cases where at one point you had an error in the file and you figured it was down to spaces? You fixed that issue, it still didn't work but from that point you never thought to question the assumption.

I find myself doing this sort of thing all the time..

Wow! Is this a new feature? I swear it wasn't there when I looked into it a few years ago. Thank you from the bottom of my heart!

Vivaldi is the only browser where you can actually disable Ctrl+W from closing a tab. And that is why fat fingered I uses it.

Unlikely. The media has already been taken over, so unfortunately people are more likely to cheer it on and blame outsiders for their problems.

The idea was, move fast and break things - but then pick them up and fix them. Companies realised they didn't really have to fix them properly as the users still stuck around.

Why?

I think this chap is just joking.

Interesting. On the pricing page, there are still limits placed on the usage. How restrictive have you found them?

What are the best open models?

Thank you, I'll look into it. For someone who is used to just working with second hand thinkpads, this stuff gets expensive fast!

How good are local LLMs at coding these days? Does anyone have any recommendations for how to get this setup? What would the minimum spend be for usable hardware?

I am getting bored of having to plan my weekends around quota limit reset times...

You could make it happen in about a week and $50 worth of tokens.

I don't think it's so clear cut. The problem is that his personality defects have allowed him to be influenced by people who are truly malevolent. Those people lurk more in the shadows and so avoid the condemnation that they deserve. Trump is their obvious useful idiot with the target painted on his head.

I've worked at companies before where they have balked at spending $300 to buy me a second hand thinkpad because I really wanted to work on a Linux machine rather than a mac. I don't see them throwing $unlimited at tokens to find vulnerabilities, at least until after it's too late.

I get the ocassional file named `1` lying around.

Have you tried reading the documentation it generates?

As someone in the UK for whom that link is blocked, I wonder if that meme is doubly apt.

I'm largely just thinking $HUGE when throwing out that number, but there are plenty of companies that have cloud costs in that range. A quick search brings up Walmart, Meta, Netflix, Spotify, Snap, JP Morgan.

What is the upper limit of Hertzner? Say you have an AWS bill in the $100s of millions, could Hertzner realistically take on that scale?