[hatenberg]

Even with RAG you’re bounded at some 93%, it’s not a panacea.

[scarface_74]

How are you bounded? When you can easily check the sources? Also you act as if humans without LLMs have a higher success rate?

There is an entire “reproducibility crisis” with research.

[hatenberg]

False equivalence. Humans fail in predictable ways that can be mitigated though process and training.

Try training an LLM.

[scarface_74]

How are the results any different? You can’t completely trust human output. There are all sorts of cognitive biases that come into play.