pixlmint

You're mixing motivation and end goal. Just because their motivations aren't purely charitable doesn't mean the end goal must be nefarious.

If not even OpenAI can properly box in their models I definitely won't trust myself to do so with the very limited time available to me, and instead just use a standard that's already defined, and proven to work.

What if I don't want my agent to have terminal access though? I get the feeling many people here simply never worked with smaller models, those will confuse cli args really quickly once context expands, and then you have no idea what damage they might do. With MCP's, they get just the access they actually need. Is the Principle of least privilege just not something we want to apply anymore?

yeh i tried pi, as a neovim user i naturally like customizability, but with how little i use agents, i want something that just works, which opencode does for me.

How is that a problem that's unique to openrouter? Who's to say when I query the Anthropic API directly, wanting to use Opus, but they determine it doesn' need Opus, route it to Sonnet instead and pocket the difference? The only difference with openrouter is that it's another layer where this type of fraud could occur.

this type of sh*t is why i'm glad i didn't switch from neovim to zed

this is a discussion we often have where I work, where we're debating removing a feature due to difficulties maintaining it and few people needing it. I usually fight to keep it, with the argument "we aren't doing it for the people that don't need it, but for the ones that do." But at the end of the day, I'm not the one who has to pay for it.

I think it' very debatable whether or not this should be a web page's behaviour.

remember, this is the worst AI is going to be...

that website is horrendous to look at on an eink display btw

you realize reading books isn't a zero-sum game right? I can still read more books, it didn't end with Clean Code

eh, when I read it as a newbie it was really helpful. still had to make my own experiences and judgments, but overall I think reading it made me a better programmer

Couldn't agree more - down to the shitty ms paint recommendation

Started out with "It's not X, it's also Y", followed by an em-dash. I didn't read any further than that.

A is good, it's grounded. C is just based

if they had any intention of doing things "the right way", they would have gone to every publisher individually and asked for a proper license.

yeah I was gonna say, it's very difficult to read on an eink display. And while we're at it, I believe my phone is set to reduced animations, which I believe is a preference that's exposed to websites, the experience would be much better without so much blinking going on.

They'll simply copy Google's playbook. First, clearly highlighted as advertisement results, usually the first three, so just with muscle memory you'll scroll down right away. Then they get bigger. Then the highlighting gets removed. Then it's just a tiny badge saying "advertisement".

didn't read the article, but just the title felt fishy because of course an inference provider wouldn't mind claiming to provide access to a mythos-class model. So far, GLM 5.2 is still my go-to, even at less than a third the parameter count compared to Kimi K3

Crazy how mighty GLM-5.2 is at less than a third the parameter count. Z.ai really cooked with that one.

And if you had to email someone in Italian, would you really do it with poor grammar? Or would you write it in English and translate it, or use a tool to ensure it's correct?

I'm not telling him to stop writing on his own and instead just let AI write for him, but there's no shame in letting an NLP tool do what it's made for and correct the mistakes you made writing in a language you aren't native to.

Exactly. And I don't want to encourage him to have the AI write the whole text, just to let it proofread what he wrote. It's a natural language processing tool. Let's use it for that.

It's kind of ironic reading a post with such bad grammar written by someone that seems to be so pro-AI

I have OpenWebui hosted on my homelab, but you can also just have it live on your machine in a docker container. I honestly just embrace the iffy feeling. Openrouter has very good telemetry (which is partly why I went with them) and it'd be pretty easy to notice when someone other than myself uses my keys. For the little agentic coding I do I like to use OpenCode, and if I need to ask a question in my editor I use CodeCompanion (neovim AI chat plugin). I quickly went to check what OpenCode does with the API key, and it doesn't seem to store it in the user config, so that's at least something. But yeah, really recommend OpenWebui as a ChatGPT replacement (though there are a lot more alternatives out there, I just already knew owui from when I was playing around with local models)

Last month, I cancelled my Claude Pro subscription and instead used those 20$ to purchase Openrouter Credits. Most of my knowledge-seeking questions can be answered by Gemma4, for basic code editing, Qwen3.6 27b is enough, and for really difficult tasks, GLM5.2 doesn't leave me hanging. I'm by no means a heavy AI user, so I'm even saving money going the API Credit route and relying on the smallest possible model depending on the task complexity.

I feel it's a little more extreme for swiss companies though, especially outside the country. My aunt who works in Rome in the tourism industry told us of a local company that had 'swiss' in the name, simply because of the positive connotation, even when they don't seem to have any relation to the country.

It's why I feel wary of making business with any company with the word 'swiss' in it's name

It'd honestly be pretty alarming. They just took the entirety of the internet to become rich, and now that they have something to take, they intentionally worsen the whole thing (by investing additional training data) to ensure resellers/ distillers get worse responses.

I'm obviously not taking the side of the resellers here - if their T&C don't allow reselling, then by all means restrict their access. But intentionally training the model to give worse responses when it sees a specific date format, would be pretty messed up.

ZHAW, a swiss institute. The locked-down browser we use is developed by ETH, a pretty highly regarded swiss university.

What do we think are the chances they trained their models to behave worse or even malicious if those special apostrophes are present in the system prompt?

I don't really see the value in testing something like this in the exam format. We have a lot of programming projects we do, where software engineering is the primary focus, and there I think is space to give an introduction on how to use AI for software engineering, what to avoid, current best practices.

But the class I was talking about in my earlier comment was specifically on the fundamentals of programming (how to write a for loop, how to write and call functions... all that sorta stuff). If you need AI to complete this, why even get the degree. Maybe in 10-20 years we'll think differently about this, but as it stands right now, I think someone holding a degree in computer science should absolutely know the fundamentals of computer programming.