Would be more efficient than compiling at run time. But if it’s for background tasks, a mechanism to cache common compiles ones might be enough? I don’t know what I’m talking about btw
@yoheinakajima
-
Code Organization: Multiple Functions with Combined Top-Level Imports
By
–
True, but having files with multiple functions but then combining imports at the top, with some code outside of functions…
-
Code as Structured Database Data vs File Systems
By
–
call me crazy but i think code should be stored as structure data in a database, not unstructured data in folders
-
Model Quality, Scarcity Psychology, and Future Pricing Impact
By
–
agree. so it's perhaps not as much as the model quality driving this – but the psychology around scarcity, time, and price. when this model is fast and cheap later, what happens? (back to shotgun probably)
-
Writing Detailed Prompts: Essential Practice for AI Interactions
By
–
I know what you mean here… and I feel like I’m doing the same – but shouldn’t we have been doing that before anyways? (writing detailed prompts)
-
Building Autonomous Agent Frameworks for AI Development
By
–
actually, "build me an autonomous agent framework" is what i would try
-
Reasoning tokens: tracking, feedback, and model consistency challenges
By
–
Having another token type would add complexity. Do you track and store reasoning tokens? If the initial reasoning is off, and you provide it feedback, how well will it guide the next reasoning, especially if the model drops those tokens (or so it seems that way based on how I’m
-
Model Outputs Separated Thought Chain Technique Explained
By
–
So it seems like there is a “thought” output from the model before the “response” output, essentially having it do CoT that way and removing the “thought” part
-
New AI Model Launched and Available for Testing Today
By
–
announce and roll out on same day? nice! don’t see it yet in my model picker, but looking forward to try!
