I'm conflicted, you can slow down and take all the time you need to understand and ask to clarify further.
Why agents are bad pair programmers
201–210 of 239 posts
Re: Why agents are bad pair programmers
#202Earlier quoted context omitted.
LLMs currently can generate a few thousand lines of coherent code but they cannot write a cohesive large scale code base. But LLMs are very good at writing SQL and Cypher queries that I would spend hours or days figuring out how to write.
Agreed. I find it interesting that LLMs seem pretty good at spitting out SQL that works well enough. But on the other hand LLMs seem pretty awful at working with CSS. I wonder if this is due to a difference in the amount of training data available for SQL vs CSS, or is this because CSS is a finicky pain in the ass when compared to SQL.
There should be a insane amount of CSS on the web but CSS output is primarily visual so I think that makes it hard for a text only model to generate.
Re: Why agents are bad pair programmers
#203Even humans are bad pair programmers, I always try to steer away from projects or companies that have drinken the whole XP kool aid.
Re: Why agents are bad pair programmers
#204Earlier quoted context omitted.
> This ensures the LLM has a complete understanding of the overall goals Forget about overall goal. I have this simple instruction that i send on every request "stop after every failing unit test and discuss implementation with me before writing source code " but it only does that about 7 times out of 10. Other times it just proceeds with implementation anyways.
Ive found similar behaviour with stopping at linting errors. I wonder if my instructions are conflicting with the agent system prompt.
System prompts themselves have many contradictions. I remember hearing an Anthropic engineer (possibly Lex Fridman's interview with Amanda Askell) talking about using exaggerated language like "NEVER" just to steer Claude to rarely do something.
Re: Why agents are bad pair programmers
#205Earlier quoted context omitted.
Thank you for the reply. What do you mean by "AI mandates"? Does it mean your company has an explicit policy allowing sharing code with AI services?
Sadly, I mean my current employer is doing the whole "tracking to see AI usage rates" and basically checking in performance reviews if people are using as much AI as the AI sales people told the CEO people need to use. We're a SaaS company so we own all our code.
That's hideous.
Re: Why agents are bad pair programmers
#206I've been considering a... protocol? for improving this. Consider this repo: foo.py bar.py bar.py.vibes.md This would indicate that foo.py is human-written (or at least thoroughly reviewed by a human), while bar.py is LLM written with a lower bar of human scrutiny. bar.py.vibes.md would contain whatever human-written guidance describes how bar should look. It could be an empty file, or a few paragraphs, or it it coul…
I think coding will eventually go away in favor of models with metadata built around them. How many times did you have a mutation operation where you had to hand code the insert of 3 or 4 entities and make sure they all come back successful, or you back out properly (and perhaps this is without a transaction, perhaps over multiple databases). Make sure the required fields are present Grab the created inserted ID Rins…
> I think coding will eventually go away in favor of models with metadata built around them.
You can pry my understanding of, and desire to use, traditional programming languages from my cold dead neurons. The entire point of computer systems is that they automatically and unerringly follow precise, explicit instructions.
Re: Why agents are bad pair programmers
#207Earlier quoted context omitted.
LLMs currently can generate a few thousand lines of coherent code but they cannot write a cohesive large scale code base. But LLMs are very good at writing SQL and Cypher queries that I would spend hours or days figuring out how to write.
Agreed. I find it interesting that LLMs seem pretty good at spitting out SQL that works well enough. But on the other hand LLMs seem pretty awful at working with CSS. I wonder if this is due to a difference in the amount of training data available for SQL vs CSS, or is this because CSS is a finicky pain in the ass when compared to SQL.
interesting. I've been having a great time telling the LLMs to generate CSS for me so I don't have to fight with tailwind
Re: Why agents are bad pair programmers
#208I think this has put into words a reason why I bounced off using AI this way, when I need something done I often have a rough idea of how I want it done, and how AI does it often doesn't match what I want, but because it's gone off and written a 2,000 lines of code it's suddenly more work for me to go through and say "Ok, so first off, strip all these comments out, you're doubling the file with trivial explanations o…
I honestly don't expect to use AI tools extensively for code generation until we figure out how to have the models learn and become accustomed to me aside from clever context prompting. I want my own models derived from the baseline.
That said, I also value not becoming too dependent on any service which isn't free and efficient. Relying on a CNC machine when you never learned how to whittle strips me of a sense of security and power I'm not comfortable with.
Re: Why agents are bad pair programmers
#209Even humans are bad pair programmers, I always try to steer away from projects or companies that have drinken the whole XP kool aid.
Indeed, this submission is also a good article on why pair programming often fails with humans.
It's not that AIs are bad. It's that pair programming is (often) not effective. In the majority of cases, one side dominates the other.
In my experience, a modified pair programming system works better where the two of us discuss the problem to be solved, then each of us goes off for a few hours independently coming up with ideas, and doing experiments. We then get together, discuss our findings, and finalize a plan of attack. And then pair programming helps as we're both at the same level and on the same page. But even then, having to watch someone else's screen (or have people interrupt you while you're typing) is a pain.
Re: Why agents are bad pair programmers
#210I think this has put into words a reason why I bounced off using AI this way, when I need something done I often have a rough idea of how I want it done, and how AI does it often doesn't match what I want, but because it's gone off and written a 2,000 lines of code it's suddenly more work for me to go through and say "Ok, so first off, strip all these comments out, you're doubling the file with trivial explanations o…
> It's like working with someone on their first day. This matches my experience exactly, but worse than working with a human on their first day, day 100 for an AI is still like working with them on their first day. Humans have effectively infinite context windows over a long enough period of time, AIs context windows are so constrained that it's not worthwhile to invest the effort to 'teach' it like you would a junio…
It’s not really that humans have infinite context windows, it’s more that the context windows are a very poor substitutes for long term memory.
Memory even in a text heavy field like programming is not only text based so it’s often hard to describe for example an appropriate amount of error checking in prompt.md. Giving a person with anterograde amnesia a book of everything they know - no matter how well indexed or how searchable will not fix the lack of long term memory.