Why is that? I know that some US-based news websites choose the nuclear option of completely disabling access to EU-based users instead of complying with EU laws. But weather app? What problem do they have with supporting EU users?
By providing product or services of value, not by maximing profits at any cost (definitely not by taking advantage of people, shortcomings of rules/laws, ... , or by harming people, ... , environment)
In Poland, before the last presidential election, a member of one candidate’s campaign team had a moment of accidental honesty. Asked whether his candidate would pledge not to raise taxes after winning, he replied: “Well, what’s the harm in promising?”
I have a specific use case (financial analysis), that is at the edge of what is possible with this models (accuracy wise).
Gemini 2 was the beginning, you could see this technology could be helpful in this specific analysis but plenty of errors (not unlike a junior analyst). Gemini 2.5 flash was great actually useable, errors made were consistent.
This is where it gets interesting, I could add additional points to my system prompt, yes it would fix those errors but it would degrade the answer elsewhere, often it wouldn't be incorrect but merely much simpler less nuanced and less clever.
This is where multi-agents helped it actually meant the prompt can be broken down so that answers remain "clever". There is a big con to this, it is slow, slow to the point that I chose to stick with a single prompt (the request didn't work well operating in parallel as the other prompt surfaced factors for it to consider).
However Gemini 3 flash is now smart enough that I'd now consider my financial analysis solved. All with one prompt.
It's hard to accurately measure but one advantage that the multi-agent approach has seems to be speed. I routinely see Sisyphus launching up to 4 sub agents to read/analyse a file and/or to do things in parallel.
The quality of the output depends more on the underlying LLM. GLM 4.7 isn't going to beat Opus but Opus with an orchestra seems to be faster and perhaps marginally better than with a more linear approach.
Ofcourse this burns a lot of tokens but with a cheap subscription like z. ai or with a corporate budget does it really matter?
Soo instead of solving the problem that the university supposedly doesn't have the money to have normal oral exams, they enshittified and techbrosified the entire process?
Thank god I had a chance to study in pre-AI times.
[1] - https://www.youtube.com/shorts/9p0CwDNM9Ps