A perfect use case of adversarial training.
@ylecun
-
Reinforcement Learning Limitations on Fine-tuned Model Prompts
By
–
No, RL doesn't fix it. It merely makes e smaller for prompts present in the fine-tuning set.
-
LLMs and Code Generation Systems: Clarifying Autoregressive Architecture
By
–
1. I never said LLMs were not useful 2. Code generation systems are not strictly auto-regressive LLMs. They produce multiple outputs and pick the best ones. 3. Your argument is as if I said "perpetual motion is impossible" and you responded "meanwhile, it's been 300km since I
-
Autoregressive Models Error Propagation in Discrete Sequences
By
–
That's a ridiculous argument. – all auto-regressive models diverge, whether they are generative (in input space) or not. – for discrete symbol sequences, the probability of correctness decreases exponentially with the sequence length, assuming independence of errors. – THAT
-
Clarifying the utility debate around large language models
By
–
I never said LLMs were not useful. We're discussing a different question here.
-
Error Recovery Impossibility in Autoregressive Models
By
–
You didn't understand either. Yes, the independence of errors is an assumption, which may or may not be reasonable. No, errors are NOT RECOVERABLE in an auto-regressive setting because the set of correct answers form a subtree in the tree of all possible sequences. Once you get
-
Autoregressive Prediction and Stochastic Generation in AI Models
By
–
No. Auto-regressive prediction produces a single path in the tree of possible sequences. At non-zero temperature (stochastic generation) the potential paths form a subtree of the full tree, or rather, a distribution over all paths in the tree. If you threshold all the paths
-
Retrospective Skepticism on OpenAI’s GPT-2 Safety Concerns
By
–
I trolled OpenAI when they didn't initially release gpt2 because oooooh soooo dangerous
-
Yann LeCun Clarifies Origins of LeNet and LeWorldModel Names
By
–
For the record l, Randall picked the name LeWorldModel. And Larry Jackel picked the name LeNet back in at Bell Labs in 1989.
Not me. -
Closed AI Models Benefit From Open Source Without Contributing Back
By
–
Let's be real, all closed models profit from open models WITHOUT GIVING BACK.