pixlmint

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.

all our exams are in-person.

I'm currently getting my Bachelor's in Computer Science, while in-person is absolutely necessary, it doesn't necessarily need to be hand-written. We now have the exam questions printed out, and we respond on the online exam platform, just like we would before. It is explicitly stated that no aids, including AI, are permitted. There's usually the prof and at least one more TA walking around the room, if anyone is seen with something other than the exam platform open they fail the exam.

Some profs also started requiring special software for doing the exams, which works fine but is pretty annoying to use since it requires Windows, but that application basically hijacks the OS, making it impossible to navigate to any different webpage/ application.

In 2024, we had some coding exams, and AI was explicitly NOT forbidden, which lead to them making the exam more difficult (because with AI, you can solve it so much more quickly, so gotta make it harder), which was really annoying, because it made it practically impossible to solve it yourself because of the time crunch. I hope they realized how wrong that was.

I can only speak from my perspective, as someone who's lightly neurospicy with a good serving of crippling social anxiety on top, but having to jump on a quick discord call with the maintainer of a project I was excited about wouldn't be a deterrent to me.

Yes it sucks, but it's better than not regulating whatsoever, and at least this way I could be more certain my contributions didn't get drowned out.

I'm pretty sure decimalenough was talking about having the project structured in an org and only allow org members to contribute, not to automatically allow contributions from people that are members of a completely unrelated, corporate-managed org like google.

JetBrains Mono does make it very hard to justify spending anything more than nothing on a good font though.

> Once most of the bugs are fixed

my brother in christ, I hope you're actually trying to be funny here.

This is cool, I vibecoded something similar for a school project, but this looks much more mature, thanks for sharing!

Anthropic has some very interesting views on Intellectual Property xD

Did you have your agent talk you into making this something separate over building on top of git?

Do they do the same when using the model through API in something like Opencode?

I cancelled my claude pro a couple weeks back. Had some doubts over it, but not anymore

Like I said, I never really used it for agentic work. I had previously evaluated locally runnable models with opencode (such as qwen3-coder), but found that it wasn't really feasible.

Since then I've adopted a different philosophy, and I actually prefer it this way.

I still very much enjoy doing most coding myself, but when I tried using tools like Claude Code, it felt very difficult to return to the codebase after letting Claude make some changes. Maybe that's just because of poor AI-use discipline, I don't know. But with smaller models, that's not even an issue. I can't just let it do all the coding and thinking for me, however if I can describe a function I want to great detail in plain english, then Gemma can write it for me, and it will most likely work. It's perfect for boilerplate.

I also recently worked with a web framework I'd never worked before, though I'm deeply familiar with other ones. So I asked it "I know how to do this in Y framework, what's the best-practice approach to doing it in Z framework?" and it was incredibly helpful, even pushing back on some of my 'bad' attempts at solving a problem.

I think GPT5.4 mini might fall into a similar category, in that it probably performs best when not overwhelmed with too many tools/ skills/ mcps, instead being given clearly defined tasks by an orchestrator model. I call those my token burners, as they're super cheap to run and have high tokens/second.

I’m working on my developer portfolio that deeply incorporates the forgejo API, which is where I host my code. It basically gives a personalized dashboard for my personal projects.

“Moving lines of code” is a very peculiar eval tbh. I’ve never used Gemma for agentic tasks, but did have it write code, including multi-turn, and I was very positively surprised how well it performed.

I use novita ai

Like I said in my original comment, it’s fine for non-coding tasks, meaning I primarily use it to answer questions

Quit my Claude pro subscription last week and purchased credits for an API inference provider. I think I might even end up saving money, since I really don’t use AI that much, and I actually found that gemma4:31b is fine for most of my non-coding inquiries.

Yup, I always phrased this as “if you can’t be arsed to write it, I won’t read it”

Holy typo… does the one world not have proofreaders?

I absolutely love the design! Thanks for sharing

the idea that llm's can't help if you're missing domain knowledge is crazy.

As a software engineer I am so deeply ashamed of how quick so many in the field have done a complete 180 on "productivity cannot be measured by lines of code" to wearing lines of code like a badge of honour.

I wonder what will happen once these guidelines end up in the LLM training datasets

Such a cool project! Now it's just missing search and a request for donations

GitHub centralizes 2 things: Authentication, as well as Repository Hosting.

Does the code really need to be hosted in a central location like this? (Clearly not, which is why people are leaving GitHub in the first place)

But the one part GitHub provides that's genuinely valuable is the social aspect, and when you get a PR from a user named torvalds you can trust that this is in fact Linus. This isn't the case with more distributed systems.

That's why I'd really like to see some entity handle just the auth/identity providing. Forgejo/ Gitea/ Gitlab instances can then choose to use that. Then, for example if you want to take on another contributor and they have their own forgejo instances, you can invite them through this provider, when they fork your repo it ends up in their own forgejo, and they can easily create PR's into your repo.