Eh. I help run a service for coding games in Godot with AI (https://ziva.sh/) and we see users who are paying non-subsidized prices on small models produce some really good stuff. I would agree most services are selling borderline snake oil and evaporating lakes of water to get their thing working, but if you invest in genuinely good tooling, it’s affordable and works
I don’t get why agent based small models are not used more. Like.if the user asks.for code, load a code only model. If they want an image, load an image only model. If they want a bedtime story, load that. Etc.
Not really supporting AI, but it feels like a way these companies could reduce costs etc, instead of these giant all or nothing models.
Plus they could reduce pre prompting maybe? Because the coding model has no idea how to say, “make a naked celebrity image.”
Eh. I help run a service for coding games in Godot with AI (https://ziva.sh/) and we see users who are paying non-subsidized prices on small models produce some really good stuff. I would agree most services are selling borderline snake oil and evaporating lakes of water to get their thing working, but if you invest in genuinely good tooling, it’s affordable and works
I don’t get why agent based small models are not used more. Like.if the user asks.for code, load a code only model. If they want an image, load an image only model. If they want a bedtime story, load that. Etc.
Not really supporting AI, but it feels like a way these companies could reduce costs etc, instead of these giant all or nothing models.
Plus they could reduce pre prompting maybe? Because the coding model has no idea how to say, “make a naked celebrity image.”
It can just fail and say “I can’t do that dave.”
This is more or less what bigger models do. They analyze your prompt to figure which model to forward your request to.
ah yes, but these companies get so wet thinking they’re creating artificial general intelligence (which, of course, will never be realized in an LLM)