I always thought that the frontend of "Ai" is awful, but now I know it for sure:

OAI5.1+ is good, but chatgpt sucks, it doesn't have gmail integration and barely able to do anything but basic retrieval from the integrations it actually has.

Opus is amazing, but claude web is mediocre at best. It has a very limited set of integrations even after 2 years, some don't even work (clay), and it uses way too many tokens to do basic stuff.

XAi is ok for social queries but grok is very bad. Its memory is basic, and the grok teams takes ship features 18 months later.

in 2024, i thought the problem is that all of this is new. "they just need a little more time" I told myself, but the truth is that the scaffolding is truly rubbish. Other the claude (which is barely good), these products are not what we were promised in this cycle. If we allowed any Ai, even the most basic models to build the frontend for chatgpt or grok, it would have done a better job! At the very least it would have shipped more features.

But why even build a generic feature of top of the LLM!?! That was the old Saas world where we had no option but to gather millions of people some place and shove the same recipe down their throats. That is no longer necessary, we can give users the ultimate Ai by just getting out of the way and allowing the user to tell it's Ai how to design the experience.

This is why openclaw ate all of the market, because it actually is an agent. It is built by the user not by a team in SF thinking they know what users need. Not to mention that an agent that has access to the end-user UI can do 10x more stuff.

-----------------------------

It's really a shame if I had to build this because nobody else is, I am barely technical enough to use openclaw.