[dead]
I wish benchmarks tracked how often you have to undo changes the model made on its own. Sometimes the less ambitious model is just easier to work with.
[flagged]
Maybe the practical path is to separate fast-changing memory from slow-changing weights. Most things an agent learns during use probably don't need to become parameters immediately.
I tried Jev a bit, and the zero-shot performance already felt good enough to be useful. If you find the right place for that tradeoff, I don’t really see why “you could fine-tune BERT” is much of a criticism.
[dead]
[dead]
[dead]
I wish benchmarks tracked how often you have to undo changes the model made on its own. Sometimes the less ambitious model is just easier to work with.
[dead]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
Maybe the practical path is to separate fast-changing memory from slow-changing weights. Most things an agent learns during use probably don't need to become parameters immediately.
I tried Jev a bit, and the zero-shot performance already felt good enough to be useful. If you find the right place for that tradeoff, I don’t really see why “you could fine-tune BERT” is much of a criticism.