WA

Not saying that it isn't possible, but stuff like this does need the human touch.

Why? I don’t like Discourse and Flarum that much. I want an even simpler solution with fewer bells and whistles.

But I guess the market is dead anyways for forums. I might replace my phpBB instance that has been running for 15 years.

I vaguely remember an article arguing that companies are basically a form of AI, because in a way, there are processes and systems and the whole thing is more than the sum of the humans working in it or something.

Now replace "AI" with "company" in this sentence of yours and we are already there. The exploits being the gigantic slot machine of social media, notifications, short-form content and endless scrolling.

But thanks for clarifying!

Now people live way longer, but the retirement age never got adjusted properly to the new reality. So 15-20 years of retirement is the new normal.

In addition, way fewer young payers for the now old.

Work for companies (as a consultant?) to help them implement LLMs/AI into their traditional processes?

Edit: Do you use reasoning models that introduce way more tokens into the context at all or prefer simpler models?

- The same spec is processed by the same LLM differently when implementing from scratch. This can maybe mitigated somewhat by adjusting the temperature slider. But generally speaking, the same spec won't give the same result unless you are very specific.

- Same if you use different LLMs. The same spec can give entirely different results for different LLMs.

- This can probably mitigated somewhat by getting more specific in the spec, but at some point, it is so specific as being the code itself. Unless of course you don't care that much about the details. But if you don't, you get a slightly different app every time you implement from scratch.

- Gemini 2.5 pro has "reasoning" capabilities and introduces a lot of "thinking" tokens into the context. Let's say you start with a single line spec and iterate from there. Gemini will give you a more detailed spec based on its thinking process. But if you then take the new thinking-process spec as a new starting point for the next iteration of the spec, you get even more thinking. In short, the spec gets automatically expanded by the way of "thinking" with reasoning models.

- Produced code can have small bugs, but they are not really worth to put in the spec, because they are an implementation detail.

I'll keep experimenting with it, but I don't think this is the holy grail of AI assisted coding.

In my case: German and English. I don’t want either to be translated to the other, but no chance. If you switch languages in the UI, you will get the garbage translated titles.

Otherwise, why spend 3 billion if you could have it cooked up by an AI coding agent for (almost) free?

Do you also love these kinds of people?

> destabilisation operations

This might actually start to become more of a self-inflicted wound. The uprise of right-wing parties is already happening in the EU. Mostly voted for by people with less education and less wealth. If we spend more money on defense and less on social security, right-wing parties might get even more traction, which causes further destabilization.

> sabotage

Yes and it sucks. There's actually not much you can do about it, because of how international waters are treated legally. But you think rearming the EU will prevent sabotage in the future? I have my doubts.

The current narrative seems to be "Ukraine is almost an EU member state and if we do not defend Ukraine, the EU will be next". Another view of the situation could be: "Ukraine is a special case and Putin would be very dumb to invade the EU".