News for hackers. Stuff that matters.

A comment on The Bitter Lesson of LLM Extensions.

Re:The Bitter Lesson of LLM Extensions by j2kun on Monday November 24, 2025 @04:20PM (#46039476)
I don't see how "they improved the models" is related to the bitter lesson. You are still injecting human-level expertise (whether it is by prompts or a structured API) to compensate for the model's failures. A "bitter lesson" would be that the model can do better without any injection, but more compute power, than it could with human interference.
[ Parent | on HN ]
Re:The Bitter Lesson of LLM Extensions by idle_zealot on Monday November 24, 2025 @04:46PM (#46039767)
> A "bitter lesson" would be that the model can do better without any injection, but more compute power, than it could with human interference.

This is what I expected the post to be about before clicking.

[ Parent | on HN ]
Re:The Bitter Lesson of LLM Extensions by marshall300791 on Tuesday November 25, 2025 @01:38AM (#46042965)
The bitter lesson here is that it all goes back to natural language rather than lower level of abstractions
[ Parent | on HN ]
Re:The Bitter Lesson of LLM Extensions by j2kun on Saturday November 29, 2025 @04:54PM (#46091147)
I would contest that this is not a "bitter lesson" in the sense that it has not been demonstrated repeatedly over decades as a truism of computer science.
[ Parent | on HN ]