This article was written before Anthropic added the Projects feature for Pro and Team users [1].
I spent some time yesterday experimenting with Projects, and, like Artifacts, it looks really useful. I like the idea of being able to have multiple projects going simultaneously, each with its own reference materials. I don’t need to use it in a team, but I can see how that could be useful, too.
The one problem I see is that the total context window for each project might start to seem too small pretty quickly. I assume, though, that Anthropic’s context windows will be getting larger as time goes on.
I wonder what other features Anthropic has in the works for Claude. My personal wish is for a voice interface, something like what OpenAI announced in May but has now put off until later this year.
From my reading there's nothing here that's specific to Anthropic, right? Any app like Chatbox, Msty or other could implement their own version of Projects based on any of the available models. (Maybe even Notion...) The API for creating an assistant with a pre-baked context is also available.
These sort of basic features seem like the hardest thing for AI companies. OpenAI only recently added a way to search all your chats. Gemini still doesn't have that.
Which is still horrifically slow and unoptimized. I’m not sure why streaming tokens from an api into an electron app is difficult but OpenAI managed to bungle it somehow.
Interesting, and even wilder that it’s buggy like that. I get that desktop apps are probably not OpenAI’s expertise but the app is unfortunately pretty unusable most of the time as of the writing of this comment. You would think for the amount of money they pay their engineers something better would have been released.
Unusable in what way? I don't personally find the macOS app to be "unusable" at all.
Also, you may be underestimating how buggy Swift and the rest of Apple's stack are. It's hard to get those bugs resolved unless you happen to work at Apple. Thus, a lot of time is spent working around bugs up the stack. So I don't find it surprising that a company moving fast like OpenAI ships _some_ bugs. The mac app just came out this month? Give it time.
No, I think you’re right. It’s just a matter of convenient tooling. I have been doing similar tasks with ChatGPT and Gemini, but, in the standard web interfaces, I end up uploading the same reference files multiple times and I tend to lose track of previously used prompts and unfinished projects. Anthropic’s Projects should make it easier for me to pursue multiple projects with different contexts at the same time.
The fact that Claude 3.5 Sonnet also seems smarter than the other current flagship models makes the Projects feature that much more attractive.
Maybe if I were smarter I wouldn’t find much use for Projects.
I'm far more excited for Projects than the other stuff. OpenAI's Memories is their lock-in for me; I'd have switched to Claude if Anthropic had something better. Projects sounds like an even better approach.
Game dev. It keeps tabs on the type of game it is, background, genre, classes, theme. Notably the difference between one decision and another - it takes note when I say "Instead of Y, do X". Like if I show a preference of Chinese names, it'll give me more of that.
I spent some time yesterday experimenting with Projects, and, like Artifacts, it looks really useful. I like the idea of being able to have multiple projects going simultaneously, each with its own reference materials. I don’t need to use it in a team, but I can see how that could be useful, too.
The one problem I see is that the total context window for each project might start to seem too small pretty quickly. I assume, though, that Anthropic’s context windows will be getting larger as time goes on.
I wonder what other features Anthropic has in the works for Claude. My personal wish is for a voice interface, something like what OpenAI announced in May but has now put off until later this year.
[1] https://www.anthropic.com/news/projects