{"type":"rich","version":"1.0","title":"alp wrote","author_name":"alp (npub175…9g6w0)","author_url":"https://yabu.me/npub175nul9cvufswwsnpy99lvyhg7ad9nkccxhkhusznxfkr7e0zxthql9g6w0","provider_name":"njump","provider_url":"https://yabu.me","html":"My evolution in AI/LLM supported development over the last 3 years:\n\nGoogle Gemini\n\nTerrible, ridiculously expensive, the results were pretty mediocre. And a provider I didn’t like, but back then there wasn’t anything else around. I was constantly nervously checking the Google Cloud Console to keep the costs under control.\nResults: a few crappy little tools.\n\nA brief detour to OpenGPT’s LLM, whatever it was called\n\nBetter results, but still ridiculously expensive.\n\nClaude Code\n\nBetter and cheaper, with a flat rate of about €100 a month. For a long time, it was dumb as a rock, but the latest models were able to handle a large project.\n\nZ.AI\n\nChinese models that are much better, without the moralizing, and with a cheaper flat rate of about €55 a month. Fantastic results.\n\nPrivate provider\n\nThis feels like the next level: anonymous, pay as you go with Sats, cheaper overall, and the best models for whatever task. The only minor downside is that the models still talk too much.\n\nAnd for the last 3 days, I’ve even been using one particular provider for free while they test their infrastructure.\n\nStill: Every model is bad at design and CSS. You have to step in a lot, even with the CSS architecture.\n\nAnyone who hasn’t kept up with this progress and has spent the whole time moaning “AI sucks” has missed out and will have a hard time catching up."}
