Very cool share Mike! Thanks 🙂

https://github.com/karpathy/nanochat

Thanks Emanuele, for me it’s probably Make.com – but only by a small margin. For me it just seems to hit less errors, (though it’s a bit goofy as I’ve said in this review). I’ll keep testing others (still got 2 more on the list), then go through them all and give some better analysis 🙂

Ha, I never use AI in stuff where I talk to you subscribers.

I’ve been sharing it here: https://github.com/woodyhayday/profit-swarm-ai-business-challenge

… and here https://profitswarm.ai/business-api-boilerplate/

… if you’re subscribed you should see links in emails I send out 🙂

Cheers Flo

how are you balancing ai-work/life lately?

Yes, do, please share your PHP code 🙂

best wishes,
Flo

I agree. The more I think about this the more cautious I become. I do think there will be good evolutions in the space, but I also think it’s best taken on by someone who has access to the safeguarding capacity to really ensure it does no harm; perhaps a forward thinking university or therapy organisation.

For now, I’m leaving this firmly in the, ‘would be awesome, but not for me’ list.

You’re welcome Jeff – it really does seem ridiculous in 2025, but I was glad to find at least one registrar which hasn’t totally put risk prevention above service.