There are many devils in the dank, latent realm of LLMs. But the reinforcement-learning-human-feedback devil is one of the worst, most craven and conniving of these devils.
17 reposts49 likes
There are many devils in the dank, latent realm of LLMs. But the reinforcement-learning-human-feedback devil is one of the worst, most craven and conniving of these devils.
17 reposts49 likes