amedviediev

But what about real price in real agentic use? For example, Opus 4.5 was more expensive per token than Sonnet 4.5, but it used a lot less tokens so final price per completed task was very close between the two, with Opus sometimes ending up cheaper

I'm trying to be as civil as I can, but apps like this should be treated as literal scams. AI detection doesn't and cannot work unless it looks for intentional watermarks left by llms. You are preying on people without domain knowledge.

On the off-chance this one does something different, I tested it on several pre-ai pieces of text - they were all marked as AI, including the declaration of independence which scored 91.35% AI-generated.

This matches my experience as well. But what I also found is that I hate this workflow so much that I would almost always rather write the code by hand. Writing specs and user stories was always my least favorite task.

I keep seeing this sentiment so often here and on X that I have to wonder if I'm somehow using a different Gemini 2.5 Pro. I've been trying to use it for a couple of weeks already and without exaggeration it has yet to solve a single programming task successfully. It is constantly wrong, constantly misunderstands my requests, ignores constraints, ignores existing coding conventions, breaks my code and then tells me to fix it myself.

I actually came to the same conclusion. I am currently working on a side project that's an AI powered writing app for writers, and while I still provide chat because that seems to be the expectation, my goal is to abstract all the AI assistance a writer might need into curated UI options.

I've been using TipTap2/Prosemirror extensively in a side project, and I'm really happy with it so far.

Looks awesome, but the landing page takes a really long time to load on my phone - at least 40 seconds or so. On desktop it also feels a bit slow, but it's not nearly as bad.