Samuel Karp @samuelkarp.com · Apr 2

This talk on LLMs is demonstrating why LLMs should be used with caution; KubeCon and DockerCon are not the same conference.

70 likes 5 replies

?

Replies

nodir · Apr 3

To be fair, that's Llama 8b, a tiny stupid model

Jeff Bachtel · Apr 2

That would have been amazing if the next slide was “and that is not correct” 😂

Alastair Smith · Apr 2

🤦🏻‍♂️ (Smaller models like llama-8b are even more prone to hallucination than the larger models.)

EssayWells · Apr 2

Or, indeed, should not be used.

pa28 🇨🇦 · Apr 2

And something as innocuous as this could cause that, especially if the model is small.