Major flaw in current LLMs is them forgetting clear and simple instructions.
This is not about the context window. At least, it really does not seem like it.
You tell it to fix all tests, "do not stop until 100% completed". It agrees, fixes a few, and 2 minutes later congratulates itself for reaching 96.9% 🎉
In context files, we still need to use over the top language like **CRITICAL** or it just doesn't give a fuck.
Looking forward to the next-gen of "don't make me repeat myself" LLM tech.
Dont you think this is by design?
How llms make money?
Probable.
This way, they can still force you to do more LLM calls with your agent.
Not convinced. It's a pretty competitive landscape
I guess everything is pretty new, so better to hold yourself back, and let others reveal themselves first to win some competitive advantage.
But probably I am wrong.
So is prostitution, housing, ...
Heavy competition doesn't lead to high quality. Deception is the winning model.
While offering good enough for cheap enough.
This is the "planned obsolence" for LLMs.
It's possible. But with a low chance.
I’ve found that the more angry you get at it, the more it ignores you.
