I'm on AI Pro and have had 3.8 since announcement day, both in the Android app and in Antigravity CLI.

I just had to go check out your site with that comment. Nicely done! Was waiting for the physics simulation to either fully settle or explode, but really neither of those happened.

Yeah I wouldn’t say my own site is an example of perfect design!

The blog post says that their gains come largely from the model trying harder. So, more tokens, more time spent.

I've done this. Ask Claude to permutate a prompt and run Claude Code or a subagent to observe effects until success. Claude will iterate on the prompt faster than I could and likely catch more edge cases, too. It's one of those tasks where the end goal is very clear and the agent just needs to iterate on permutations. Arguably this is a perfect match, too, because prompt engineering is really just text generation, so why not have a text generation machine do it.

Gemini is not bad at coding? Give it a /plan and it does a very decent job in a fraction of the time/tokens that Claude needs.

Similar thoughts here. My gut tells me "if I wanted AI responses I would just ask AI", but in truth LLMs are not like Google Search. LLMs are more like a slot machine where you put your prompt in and out comes a combination of insights that are personalized to the inputs.

The header doesn't fit on mobile. Teach your agent to use Playwright MCP.

"I don't know" isn't in the training data. Nobody writes engineering books, science papers and blog posts that end with "well, I don't really know, the end".

A bit like publishing bias where only positive results end up in scientific papers.

It should be in the post-training though. Hallucination rates are a fraction of what they used to be as a result

There is a point where this kind of a pragmatic/contrarian take doesn't stick anymore. Is the net benefit of AI worth the cost of losing natural resources for billions? That's the question you're supposed to ponder, like, it's actually up in the air and not clear cut?

It's worth flipping the question around to explore how you actually think.

So rather than ask "What is the impact of AI?" which narrows your focus to the impact of AI, if you really care about the natural resources you should be asking "What has a big impact on natural resources?"

If that's AI, and you're ignoring all the things that have a far greater impact on what you claim to care about, then you should ask if you're really just looking for things to complain about around AI, and natural resources are a convenient excuse.

For example, the largest data centre in the US uses approximately the same amount of water as 2 burger restaurants if you include the water used to raise the beef used in the burgers. (https://newsletter.semianalysis.com/p/from-tokens-to-burgers...)

If you care about water resources and you're not a vegan campaigning against the beef industry, but you're focusing on AI, then you have a degree of cognitive dissonance.

Except that those are very old, very entrenched industries. We are still in the phase where we have a chance of setting some rules for "AI" before it becomes fully entrenched.