We've now fine tuned a base stable diffusion model to Midjourney levels of aesthetics (particularly in some domains).
@waitin4agi_
-
Latency Prevents Speech as LLM Interface
By
–
Some people asked why we don’t have speech as the mechanism to communicate with LLMs. Latency. The answer is latency. 3s for a round trip answer and you get BORED waiting.
-
Local LLMs reduce latency for real-time NPC conversations
By
–
So one problem with using GPT-3 or 4 in games for NPC conversations is latency. Best case you can bring it down to 2s b/w input and output. But the onboard M2 on the Vision can allow you to use local LLMs which can bring latencies down to allow for things like realtime therapy
-
Video AI Struggles with Frame Consistency and Narrative
By
–
frame to frame consistency is poor. Plus if you actually try putting narrative into it: it fails. text2img is easier because narrative isn't required.
-
Apple’s Vision Team Contradicts Face Computer Strategy for Kids
By
–
Apple: our vision team is going to make sure your kids go outside and aren't too close to the iPad Also Apple: face computer go brrr
-
Apple Introduces New LLM, Headset, and AI-Powered Mac Computers
By
–
apple llm headset
some new macs
lots of AI AI AI generative AI -
Building Magic Through Active AI Community
By
–
The magic is when have this amazing community of doers.
-
GPT-4 AutoCodePro generation costs around 8-9 dollars
By
–
if your autocodepro generations are failing and you're using your own OpenAI key, make sure you have some tokens available. ~8-9$ per GPT-4 generation (roughly).