Understanding is the new bottleneck
geoffreylitt.com
Understanding is the new bottleneck
1–10 of 259 posts
Re: Understanding is the new bottleneck
#2"I read the code." -Mitchell Hashimoto
Great code needs great understanding and agents need excellent guidance. Even in my current solo-dev work, I can't imagine making a production commit I haven't read until I understand it. I own the consequences of my code; that's a responsibility AI agents can't take.
Re: Understanding is the new bottleneck
#3I am so dying to read more about the new/current/real bottleneck!
Where is the bottleneck? WHERE?? Tell me! No evidence needed, just lay it on, man to man, thought-leader to thought-leader!
Re: Understanding is the new bottleneck
#4While the tips are good to handle the volume, I still think this sets code owner on a dangerous path.
AI have limitation and hallucinate. Complex code will be explained in hallucinated way. At some point AI will be unable to write more because the arch has become too complex or the volume of code will be to high.
The article I would like to read would suggest how to force LLM to architect the code like a solid tower instead of a pile of unstable mud.
Re: Understanding is the new bottleneck
#5I am so dying to read more about the new/current/real bottleneck! Where is the bottleneck? WHERE?? Tell me! No evidence needed, just lay it on, man to man, thought-leader to thought-leader!
Oh wait, there it is, sitting over top of the fat part and under the cork...
Re: Understanding is the new bottleneck
#6We have LLMs try to generate descriptions of PRs for us and they're pretty universally disliked. They're always overly-complex descriptions of the mechanical changes and have no sense of motivation.
Also, a huge reason to understand the code yourself is to make sure the LLM isn't wrong, but this doesn't work if an LLM is itself generating the understanding.
Re: Understanding is the new bottleneck
#7pfft...I'm way past understanding
Re: Understanding is the new bottleneck
#8We have LLMs try to generate descriptions of PRs for us and they're pretty universally disliked. They're always overly-complex descriptions of the mechanical changes and have no sense of motivation. Also, a huge reason to understand the code yourself is to make sure the LLM isn't wrong, but this doesn't work if an LLM is itself generating the understanding.
I don’t know. From my experience I get pretty good descriptions of PRs if I ask the right questions and provide some context.
Re: Understanding is the new bottleneck
#9While the tips are good to handle the volume, I still think this sets code owner on a dangerous path. AI have limitation and hallucinate. Complex code will be explained in hallucinated way. At some point AI will be unable to write more because the arch has become too complex or the volume of code will be to high. The article I would like to read would suggest how to force LLM to architect the code like a solid tower…
I feel if you still architect the code and guide the LLM, it will do a pretty good job. Maybe one day the LLM will be able to do all the system architecture but that’s probably still quite some time out. I don’t even know if that’s possible considering different business needs and other factors that aren’t technical.
Re: Understanding is the new bottleneck
#10For me the solution has been to throw away the code I don’t understand. I let the agent write the code, and if when I read it it seems unclear or needs a lot of explanation from the agent, I just throw it away and start over, or do it by myself.