N
I have the feeling that this comes from a fundamental misunderstanding of the topic.
Sure, if you use LLMs as a tool to produce 'code', you *might* find it useful. (Just like the techbro-rideshare will *move* you around)
But to have agency over your software, you need to work on the *system* that the code represents, and at that LLM's just fall apart.
@mnl @david_chisnall @mjg59 @ignaloidas
even reading the first page.
Generally, this assessment of the overall book extends to each page, even if it contains pages with errors.
For llms, there is a probability that each query is resulting in garbage. In the book-analogy, it is as if each page is written by a different author, some experts, some crooks
Except no page is attributed, and guessing who wrote what page is up to the reader.
There is no model to be build around that fail-mode
2/2
@mnl @david_chisnall @mjg59 @ignaloidas
Yes, but that is also not the argument.
If you read a book to extract information, you already have a mental model of the failure modes (or can build one, like students do)
- Is the author known to be proficient in the space
- Is the publisher reputable
- Is the book 'new'
Depending on the answers to those questions, you either take the content as absolutely correct, likely correct, plausible, or problematic. You can know those things before
1/2