Yeah, the space moves so quickly that I would not want to couple the hardware with a model that might be outdated in a month. There are some interesting talking points but a general purpose programmable asic makes more sense to me.
I tend to agree. I don't know whether it's Altman or someone else who makes these deals but OAI have made some brilliant moves and partnerships. Anthropic's tech is great but the OAI makes great business moves.
Altman is the startup idea king. He should definitely know his moves.
Even worse for antrophic is the renaming from clawd to openclaw. It is almost comical now that Peter had to rename it and now it sounds more like OpenAI
While Anthropic certainly benefits from the privacy/security overton window shifting, I've never seen Claude or people from Anthropic mention these projects so I have no evidence to include them
I want to set this up but I'm concerned about the privacy and security risks. On the one hand, person data is flowing through cloud models. Then there's the risks of prompt injection and such.
I thought about running it locally but it gets expensive.
Those that have taken the plunge, how did you make peace with these trade offs?
This is one of the biggest issues with hosted models used via subscription. You have no idea what level of quality and accuracy you are consistently getting. That's why it's cheaper - because they can nerf it as they wish and most consumers would be none the wiser.
reply