I think the next ChatGPT moment we are going to see is just in time interfaces.
ChatGPT got popular, it had a very familiar interface, it was chat and it was like chatting to a very intelligent human. Later came Canvas where if it thought it was writing a longer text it could write it a kind of like text editor, but so far we have not seen anything more advance.
ChatGPT was a next generation of LLM, OpenAI used to have a playground where you could use GPT3 and it was just a textarea where you could have GPT3 continue your sentence.
It was quite difficult to use, and it did not feel like talking to anybody since it was more like continuing your own sentence, but it felt like magic.
Conversations are now longer than ever, combined with function calls and including a lot of text like files, the old method is beginning to break down. Sending infinite messages back and forth, making sure to use the prefered Context cache, and having to support Voice to text; you will be seeing very long processing time!
When Anthropic annonced Claude 4 and together with Claude Code I was pretty much on board. I had been using Windsurf and it was funny how you learnt how each model behaved and it was clear that Claude Sonnet 3.7 was the most intelligent.
With Windsurf it worked like this:
Claude Sonnet 3.7 was however the model that most likely would edit another file without being asked to. Gemini 2.5 Pro would pretty reliable edit a file, but would selfdomly go out of its way to do something smart and think bigger.
You want to put a AI agent online so that people can try it out and benefit from it. The easiest way would be to require everyone to sign up as a user. We know that is not a good user experience, it takes time and may be too much effort if it is just for a search on a website.
The solution is often a captcha, a small widget that tries to detect if you are a real human. It often relies on huristics and metrics. In the GDPR ages, they are forced to not save personal data, but it then makes it harder to disguinsish who is the good and bad if you can't have history on a user.
Why do we need captcha? Two reasons:
to protect the valuable data we have
prevent abuse which cost money
What are our options to prove that we are human that we can use, that is also cheap and fit our usage case for search:
It is funny how every AI company has copied ChatGPT interface (Claude, Deepseek, Mistral, all history on the left, a small text box in the middle and a conversation interface once you begin writing. It is boring.
Here is what I would suggest doing better:
Favorite conversation
Make it possible to favorit certain conversations, some conversations you want to come back to.