points by sdevonoes 4 days ago | 0 comments
Is it just me or others also feel like “no respect” for this kind of knowledge? Before I was proud to know about TCP connection protocols, 2FC, parsers, compilers… and much of that knowledge had applications on the software I had to build.
But nowadays I have very little interest in knowing how “to prompt better” or why after around 100K tokens of context things start to suck for agents, or compiling tons of MD as “skills”. I don’t find that stuff challenging or interesting (granted, I don’t mean that I know all about it) and I have the feeling that it’s not like learning about operating systems or relational dbs.
I think part of my overall rejection to LLMs comes from this (of course the actual knowledge of how LLMs work under the hood is super interesting, but not their usage Id say)
Knowing TCP connection protocols or deep compiler infra is impressive insofar as it's a mountain of knowledge that you've conquered and can stand on with a nice view, whereas "context engineering" and current AI engineering is a murky domain with no correct answers because... nobody alive knows the correct answers.
There's something different about wading forward into unexplored territory, or being able to establish techniques that nobody has attempted before. A lot of it will be noise or garbage (especially given a lot of it is LLM code), but I'd be careful to not mistake clever greenfield engineering with garbage simply because there's not a book written about it you can use as an oracle.