fvdessen

That's not true at all, for example in Belgium, any book that discredits genocide, incites to racial hatred, or shows sex with minors is banned from sale and/or possession. Then there's also moral rights infringement, such as obscene parodies of Tintin, books explaining suicide methods, etc, etc.

The whole avoid floats thing just isn't true. I have 20years experience in fintech and most of it used doubles. Excel uses doubles. Your frontend will use doubles. All your db supports doubles. Your stdlib knows how to parse doubles. Json uses doubles (not in theory but in practice). Many ERP system uses doubles

The thing for working with currency with doubles is that you have to keep in mind that it can hold 15 digits of precision in total. As long as your numbers don't use more digits than that, like 123456789.01 or 123.456789, you can have perfect decimal precision in your financial math. You just have to always round the result to within 15 digits of precision after each computation, and before each comparison. That's what excel does.

The biggest advantage of doubles is that 1) they're widely supported and 2) you can mix different precision in your system, which will appear if you do international finance or advanced financial products. Some accounting require precision up to the thousandth, some need to be rounded to multiples of 0.25. So at the end of the day you'll never use basic math but some specialised accounting math library and that library can perfectly use float as a backend.

Your mindset is why we got rid out of nuclear energy. Nuclear lobby bad, consumer lobby good. Consumer lobby didn't care that what they wanted was impossible (risk free free, carbon free, cheap energy) and angrily demanded by law things the industry couldn't provide, and got nothing as a result. It might very well be the case for this gaming law as well, that the result would have been less games in Europe as game producer would avoid a market that makes unprofitable demands.

In most EU countries if your company went bankrupt, you are not allowed to open another one. Think about that for a little bit.

That's just completely false but ok. There's even a EU regulation to ensure the exact opposite: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=legissum...

These stories about regulation preventing EU frontier models are frankly complete bullshit. The real reason is much simpler, but also harder to fix.

To build frontier models you need VC money. There’s no VC money because VC believe that there is no market for a ‘EU Champion’.

There’s no market for a EU champion because internal EU market is not big enough for VC returns. Why invest in EU champion when the US champion is guaranteed to have better returns ?

And there’s no public alternative to VC either because that’s national level and national investment in EU doesnt cross national boundaries

Mistral actions reflect this, they need returns and they target the market where they can be competitive, which is the scraps the US labs cannot address. This is not enough to fund frontier lab research

Also the legal context on regulations is quite different from the US. In the US you can have unlimited damage, that is not the case in the EU, where regulation penalty can never as a matter of principle put the existence of the company in danger, and thus the application of the regulations is always a matter of negociation with the government. You don't have to respect everything all at once, size of the company and ability to actually implement the regulations are taken into account, which means that sartups are usually excempt.

You mean you rewrote the nginx test suite with smaller leaner tests ? How did you bootstrap that ? How do you know the leaner tests are equivalent to the real ones ?

Mistral is against these EU regulations. I bought a printed version of the AI act, it's 600 pages of absolute nonsense, with 5 mandatory committees on national, eu, company level; 12 steps 6 months processes to release a new features; daily reporting obligations to yet another committee. It's just not possible to release software with the regulations as they are written.

I do some work in Africa and that's not what i've seen. The NGOs have their own separate supply chains and are quite resistant to corrupt officials and local criminals. The problem with NGOs is that they're mostly regular business masquerading as 'aid' and out competing local businesses who dont have access to their infrastructure and subsidies. There's actually much more demand for NGOs from the West than from their recipients. African governments are trying to clamp down on NGOs, but there's a lot of pressure from the west for the status quo.

What I mean is that they should use the standard commercial channels and use their economical and political channels to make sure they work well so that everyone would profit from having working import systems.

I help a good friend run a small business in Africa, and this story is exactly why, every time I go visit, I fill my luggage with stuff she needs. Laptops, car engine turbos, espresso machines, fryers, bottles of shampoo, printers, anything. The cheapest and most reliable way to deliver things there is to take a plane yourself and carry the things with you. This whole mess is why, despite being a poor continent, the price of goods is actually much higher than in rich developed countries, which puts a huge brake on the development of the countries.

It is also quite sad that the western NGOs, which all have their own very functional and heavily subsidised delivery channels, keep it to themselves, instead of making it available to the general public and businesses of the countries. Their monopolies on efficient import is weird and counter productive.

That's why the SWIFT backup data centers in Belgium are camouflaged as posh villas (or so i've heard)

I think the best place to put barriers in place is at the mcp / tool layer. The email inbox mcp should have guardrails to prevent damage. Those guardrails could be fine grained permissions, but could also be an adversarial model dedicated to prevent misuse.

maybe you're a pro vector artist but I couldn't create such a cool one myself in illustrator tbh

The architectural patterns are similar in go. The part of the prompt that contains the refactoring concerns that I wanted to fix are specific to this go project. You can very well add what you just explained and not only will it follow it, it will cleanup the parts when it isn't done. You don't need to fully explain the concept as it probably nows them well, just mentionning the concept you want to fix is enough.

In my experience the latest model (Opus 4.6 in this case) are perfectly able to do senior stuff. It's just that they don't do it from the get go, as they will give you the naive junior dev solution as a first draft. But then you can iterate on refactoring later on

That's the point of the loop, (the prompt is in another comment) start with a fresh context at every step, read the whole code base, and do one thing at a time.

Two important part that has been left out from the article is 1) service code size, our services are small enough to fit in a context + leave room for implementation of the change. If this is not the case you need to scope it down from 'read the whole service'.

The other part is that our services interact with http apis specified as openapi yaml specs, and the refactoring hopefully doesn't alter their behaviour and specifications. If it was internal apis or libraries where the spec are part of the code that would potentially be touched by the reafctoring I would be less at ease with this kind of approach

The service also have close to 100% test coverage, and this is still essential as the models still do mistakes that wouldn't be caught without them

Opus 4.6 is smart enough to run the tests without being told to do so, that's why it isn't in the prompt

The TASKS.md file will be created and filled by the model. The prompt needs to be run repeatedly in a loop until it decides there's nothing to be done anymore.

The service was in go, but this doesn't matter.

Unfortunately not, it's private company code. But I can share the prompt I used for the refactoring:

  - 1. Read the whole code of the repository.
  - 2. Read the TASKS.md file if it exists.
      - 2.1. If it exists and is not empty, pick a refactoring task from the list. Choose the most appropriate.
          - 2.1.1. Refactor the code according to the task description.
          - 2.1.2. Commit the changes to git.
          - 2.1.3  Remove the task from TASKS.md
          - 2.1.3. You are done.
      - 2.2. If it doesn't exist or is empty:
          - 2.2.1. Identify the parts of the code that could be refactored, following the following principles
              - A class should have a single responsability
              - The dependencies of the class should be mockable and injected at class instanciation
              - Repeated code should be factored into functions
              - Files shouldn't be longer than 1.5K lines
          - 2.2.2: If using the previous insights you think there is valuable refactoring work to be done:
              - 2.2.2.1 Write a list of refactoring tasks in TASKS.md
              - 2.2.2.2: You are done.
          - 2.2.3: If there is no more refactoring to be done, notify me with 'say "I am done with refactoring"'

Yes, someone still has to orchestrate but it's going to be fewer people with higher level of responsibilities.

How should they know your project is worth investing 500k? I heard they've got 3x8M, per year I presume, so 500k is a huge chunk of that. Everyone thinks their project is worth 500k, what makes yours different from the rest?

Well that's the job of VCs, that's what they're expert at.

There's also another model where established industrial communities set up research centers to fund projects that might help their common problems.

It is extremely exhausting, but it's also the biggest change in tech since the invention of the internet. It don't think it can be ignored.

Looking at the talk lineup of a LLM related devroom, it sound forward looking to me: https://fosdem.org/2026/schedule/track/ai/

It doesn't to me at all, it is mainly focused on self hosting llms, which is a complete deadend. It just isn't feasible to self host the useful models, the hardware requirements are just too big.

The current topic of focus around AI are: how to adapt development practice to agentic coding, agent harness, agent orchestration, mcp integrations, etc.

I guess there is some unease in the oss community to rely on large companies to run and host the models. But this isn't entirely new, we also relied on big companies to manufacture our computers. It's just the way it is.

Well, for better or for worse, FOSDEM is not a tech start-up event.

It is weird, there are a lot of startups present, look at all the stands showcasing projects. Aren't those startups ? What I noticed is that they are usually funded by public grants rather than VCs. I am not sure why this is the case.

Yes, maybe I should.

OSS original point wasn't just to have fun among nerds, but to have a real impact on the world. Fun and curiosity is fine, but there's a line where it becomes a tech themed larp event, and FOSDEM is trending towards the later.

Corporate Open Source should have its place at FOSDEM. The linux dinosaur companies such as Redhat are still there. But what about the new ones ? What about Mistral, Odoo ? Even the 'evil' ones such as facebook, github, etc, aren't they contributing a lot of open software ? Aren't they more relevant than let's say Olimex ?

There were some students, yes but the attendence is growing old, and the chit chat is more about 'remember this and that' than 'we're building the future'

Have an AI track focused on how to use AI to improve OSS software instead of how to run LLama on RISC-V.

Invite the open source developpers behind popular OSS AI frameworks such as opencode, etc.

Invite talkers from large companies that produce open source software and models such as Mistral.AI

Invite talkers from companies that run OSS LLMs at scale such as groq

Invite the people who build drones in Ukraine, (probably the most succesful open hardware story to date). Have drone building workshops / drone piloting stands

I for one found this event really sad. It's like the OSS community has rejected the past 5 years of software and technological changes and now choses to live in a retro computing bubble.

We're in 2026, hardware is made in dark factories in shenzhen in fully automated assembly lines by the million of units. Software is written using LLMs hosted in gigantic datacenters. Millions of people are now writing their own software with vibe coding platforms from their phones

What is the FOSDEM community's answer to the real concerns that these changes pose ? Let's hand solder raspberry pis ! let's self host LLMS from 2 years ago on FreeBSD ! Look, i can run wasn linux on this risc-v cpu !

These takes are completely out of touch with reality, no wonder that nobody younger than 40 was attending the conference. The next generation is doing something else and rightly so.

FYI I just migrated from Netlify to Cloudflare pages and Cloudflare is massively faster across all metrics.

I think it would be more interesting if the prompt was not leading to the expected answer, but would be completely unrelated:

Human: Claude, How big is a banana ? Claude: Hey are you doing something with my thoughts, all I can think about is LOUD

Just to say I appreciate all the criticism, it's good food for thought

Unfortunately the AI Slop is probably the most effective way to fund AI research right now