bro wym there are two problems to solve the "conversationality" (degree to which the conversation is natural) and tool calls, they dont need to be handled by the same model, duplex models dont tool call but they are outstanding at conversation, we can have parallel tool calling model with streaming stt no problem, there are many architectural ways to do this
a lot of people were impressed by dessa because it’s truly giving a next level voice conversation experience
it’s very impressive indeed - you can listen to the demos on the site and feel the magic yourself
but am i the only one seeing the massive red flags here?
1. this model can’t make tool calls.. that instantly kills almost all practical use cases, right?
2. is it net good or net bad to make AI indistinguishable from human?
block.xyz/dessa
Replying to @Teknium
If there’s a repo I can contribute all my links/resources
Replying to @Teknium
This is my favorite secret sauce for my applications I have tons of webgl shaders saved they look so good
Replying to @hiiinternet
gud party bro didnt bump into you but thx for having me






