Hacker Newsnew | past | comments | ask | show | jobs | submit | parasti's commentslogin

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.


Actual announcement: https://blog.google/innovation-and-ai/models-and-research/ge...

So it's better than 3.6 Flash, at half the price. I've been pretty excited about Gemini models recently, they just feel so fast after spending most of the day at work waiting for Opus 5.


Yes, 3.6 Flash is very fast. I used to get a fair amount of usage of the Gemini Flash models on the free tier. I signed up for their $4.99/month tier (includes 400GB of Google space which was also enticing) and it turns out I only get about 15 to 20 minutes of usage before I get a come-back-in-7-days message. Comically low usage limits on that plan.


For comparison tho, 400GB of cloud storage for $5/mo is actually quite amazing even if it didn’t include anything else.

I know, it’s cloud storage, a NAS lets you own your data, but for non techies who have a bunch of photos and videos; it seems like an easy recommendation.


Is it though? Hetzner gives you 1 TB of cloud storage for 4 USD per month.


You can get Google AI Pro through verizon fios or mobile in the US and pay only 10/mo. For 5TB cloud storage, and decent gemini usage its a compelling option


> So it's better than 3.6 Flash, at half the price.

I think its the same price..


They seem to have reduced the price of 3.6 Flash at the same time that they released this 3.7 model:

https://ai.google.dev/gemini-api/docs/pricing today has 3.6 Flash at $0.75/$3.75 until December 31st 2026, then doubling.

https://web.archive.org/web/20260809105129/https://ai.google... Internet Archive copy of that page from 9th August has 3.6 listed at $1.50/$7.50 with no mention of the price changing.


I'm super curious how you make the development process interesting for him. I get that a 5yo would be good at generating ideas but how do you then go "okay, now I'll need a week in front of a screen to build all these ideas" and not have him lose interest. Do you accelerate using LLMs?


Yeah, good question! We can do a lot of the creative process on paper, with his styrofoam models, and audio effects etc without even being near the computer. Then when I need to go ahead and write code, it's not going to be that interesting for him, but I've shown him how it works and how we can change stuff.

A lot of the very technical parts are done during the evenings after he's asleep, and I think that's okay, as it'll end up in a better result the next day so he can go and test and give further feedback.

Oh yes, I eventually did less hand coding and relied more on Claude Code to get the job done. I understand the game loop, the architecture and the algorithms, which I think is important. Don't hide that under the hood.


This is precisely why I'm building Breaka Club:

https://breaka.club/blog/why-were-building-clubs-for-kids

I also attempted to make a game with my eldest daughter initially. Unsurprisingly, she didn't want to sit there watching me code or drag things around in Godot's level editor.

Admittedly, I really need to make a new blog post showing the latest improvements brought about from the in school pilot I'm running weekly at the moment.


That's a really interesting approach. I love to see the kids sitting there and drawing on paper etc.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: