daliusd

Same here, but I understand their position. Meanwhile I rely on packages publishing builds for Intel Mac in GitHub (surprisingly a lot) or building from source code. I just asked AI to build me install system.

Yes, your article was noticed in my circle, but numbers was what was lacking

It is just "putting a wet phone in rice" of AI

Still you will not be able to give any existing example that lasted longer than 100 years. There are examples like Sayfawa dynasty which is counter-example to your claim about technology being multiplier

It would be interesting to get details what’s the process behind. Can you reproduce it on personal level?

Same story in Lithuania

I am disappointed that not all your comments are this line :D

I can guess at least one valid:

* preventing North Korea, China, Russian, Iran and etc. actors from accessing service. They absolutely use workarounds to access AI, e.g. I bet there are companies who are proxy between Anthropic and those countries.

I imagine there will be quite some false positives while identifying those.

Thank you, I will check the article

That's the best we have and it is better than random internet commenters who make judgement like they have a solid evidence of what's going on. Lastly depending on outcome this can be used for more fruitful discussions in the future.

I don’t see any pro-Israel side commenter here but me at best. IMHO I do my best to keep discussion as polite as possible having in mind the sensitivity of the topic.

In this specific case it is something interesting to follow and to analyze. This will definitely have consequences on Russian-Ukrainian war too. UN overall is powerless - there are 7000+ UN peacekeepers in South Lebanon right now. What are they doing there?

Exactly

No you make fun of me and that’s it.

I guess this is sarcasm, but I don't even understand what you want to say.

Why not? There is at least theoretical chance to get some justice regarding Benjamin Netanyahu crimes if they are proved. As well Israel is democracy and can be changed. It is not like Russia where people don't have freedom of word.

What's your proposal and vision regarding Israel?

So what's your definition of genocide? Maybe we are discussing about different things.

Genocide definition is: the deliberate, systematic destruction—in whole or in part—of a national, ethnical, racial, or religious group

Israel most probably did war crimes (white phosphorus usage seems to be confirmed, while IDF says they have not used it), but I don't think that Israeli has intention to destroy Palestinians. The have intention to destroy Hamas or Hezbollah.

You are mixing war crime and genocide IMHO.

Murder and genocide is not the same. Genocide has strict definition.

I think you are right. Leadership vacuum will not resolve by itself: Iran either will go democratic way or into some internal fights (this one more probable IMHO).

Israel can do better, but Israel committing genocide is not the fact legally.

In 2 years Hormuz will not matter potentially. You can’t win with the same strategy twice.

Maybe it was for older version?

I had to double check this. Here is summary:

The model selection for title generation works as follows (prompt.ts:1956-1960): 1. If the title agent has an explicit model configured — that model is used. 2. Otherwise, it tries Provider.getSmallModel(providerID) — which picks a "small" model from the same provider as the current session, using this priority list (provider.ts:1396-1402): - claude-haiku-4-5 / claude-haiku-4.5 / 3-5-haiku / 3.5-haiku - gemini-3-flash / gemini-2.5-flash - gpt-5-nano - (Copilot adds gpt-5-mini at the front; opencode provider uses only gpt-5-nano) 3. If no small model is found — it falls back to the same model currently being used for the session. So by default, title generation uses a cheaper/faster small model from the same provider (e.g., Haiku if on Anthropic, Flash if on Google, nano if on OpenAI), and if none are available, it just uses whatever model the user is chatting with. You can also override this entirely by configuring a model on the title agent.

Invoicing app for individual workers in Europe. Currently I am focused on compliance (it is Europe after all)). Check it here: https://www.haiku.lt

They can, but should be explicitly told to do that. Otherwise they just everything in batches. Anyway pure TDD or not but tests catches only what you tell AI to write. AI does not now what is right, it does what you told it to do. The above problem wouldn’t be solved by pure TDD.

Sorry, but it is not fair analogy. It is comparison of ikea knife vs cheap chinese knife that breaks after 10 uses.

Sad that it is Chinese one.