Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Your intellectual fly is open when you use an LLM to author a post (2025)

bcantrill.dtrace.org

Post reply on HN
Print view View original

191–200 of 449 posts

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#191

Post by jeremyjh »

27183 wrote: post #165
jeremyjh wrote: post #114

Earlier quoted context omitted.

Agreed, but a lot of code doesn't need to be understood. Knowing which is which is the art right now.

Uhh... what? You'll instantaneously feel very differently when the service you're responsible for is down at 3:15am and your logs are full of stack traces that end somewhere in that code that "doesn't need to be understood". At that point, you will need to understand it well enough to fix it stat.

Test code for a new bug is a good example. You can prove the test covers the bug without understanding the test code (you need to understand the bug, of course). There are some domains/tests where you can't do that - you need to be sure its failing for the right reason, but often you can do that without understanding every line of the test code. You can extend this to lots of related test infrastructure. If you can watch playwright test the app the way you expect it to, you don't have to understand all the code.

You can also do this for apps that are just tools for your own use. You satisfy yourself that they are working, and you use them because they save your time. You review enough to be sure its implemented the way you think it is - and if it is working, that tells you quite a lot. Sometimes you will be surprised and have some time wasted.

Yes, yes - there are people who will make the wrong choices in some of these cases but that doesn't mean there are never cases where you can do it.

More broadly - anyone who works in a team is already working with code they don't fully understand. I have code I wrote years ago I don't fully understand. I trust its observable properties and its track record.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#192

Post by a2ff6eeb0 »

jeremyjh wrote: post #62

These are all important points and I love the analogy. But there is an even bigger issue with having LLMs write for you: Writing is thinking. Thinking and deciding. There have been many times when I start out writing something substantial - could be an email, a blog post, a software design document, anything - when my own views substantially changed during the writing process. Writing forces you to serialize your tho…

> You cannot outsource your understanding to AI. They are powerful tools but they do not have any human understanding - that isn't their optimization target.

Understanding is the bottleneck; the way they speed things up is by letting me outsource understanding, and get back a summary. The entire advantage to AI is that it lets me skip understanding the problem, and just get a working solution.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#193

Post by a2ff6eeb0 »

jeremyjh wrote: post #184
bcherny wrote: post #166

Earlier quoted context omitted.

(I work at Anthropic) I agree. I use an LLM to write my code, but I do all of my writing by hand, since it helps me think. It reminds me of the transition over the last year from AI-assisted coding to AI doing all the coding. At first the code output wasn't good enough, and humans read and iterated on the code all day, so the details of the source code mattered. Now, the code is largely high quality and it meets a la…

You are just talking about the output though. If you only think at a "higher level" you aren't doing the actual thinking. Its the same with code. The output may be good enough, but over time you lose touch with the details to the extent that you can no longer serve a useful steering function for the organization. Before coding agents I'd seen this with many humans when they get promoted passed the point where they wo…

Yes, of course. At some point the LLMs will also run the organization.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#194

Post by a2ff6eeb0 »

prisonguard wrote: post #170
bcherny wrote: post #166

Earlier quoted context omitted.

(I work at Anthropic) I agree. I use an LLM to write my code, but I do all of my writing by hand, since it helps me think. It reminds me of the transition over the last year from AI-assisted coding to AI doing all the coding. At first the code output wasn't good enough, and humans read and iterated on the code all day, so the details of the source code mattered. Now, the code is largely high quality and it meets a la…

You and the AI agree, but how about you and the team who will eventually read and do code review. Cognitive burden increases marginally with AI assisted coding. This is why we haven't seen big projects(think browsers and browser engines) spawning in the past year.

> but how about you and the team who will eventually read and do code review.

Why are you reviewing AI code in detail? Do you also review the assembly output of GCC line by line?

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#195

Post by zdragnar »

prisonguard wrote: post #170
bcherny wrote: post #166

Earlier quoted context omitted.

(I work at Anthropic) I agree. I use an LLM to write my code, but I do all of my writing by hand, since it helps me think. It reminds me of the transition over the last year from AI-assisted coding to AI doing all the coding. At first the code output wasn't good enough, and humans read and iterated on the code all day, so the details of the source code mattered. Now, the code is largely high quality and it meets a la…

You and the AI agree, but how about you and the team who will eventually read and do code review. Cognitive burden increases marginally with AI assisted coding. This is why we haven't seen big projects(think browsers and browser engines) spawning in the past year.

It's anthropic, of course the entire team is also using AI to do the code reviews.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#196

Post by antonvs »

jeremyjh wrote: post #122
bbor wrote: post #100

Earlier quoted context omitted.

They are powerful tools but they do not have any human understanding - that isn't their optimization target. Ofc the rest is all right on, but I'd quibble with this specific idea. LLMs are absolutely targeted at modeling human understanding, which is the same faculty that contains what we call perception (!= sensibility) and intuition (!= rationality). It would be nice to train them to be completely alien from the gr…

We don't have a reward function for "human understanding". We reward the appearance of understanding. We define goals that we cannot conceive of reaching without something like understanding happening. There is something happening, but it is alien and counter-intuitive - it makes bizarre mistakes that betray it - and we don't know what it is. I'm pretty sure it is not human understanding.

> We reward the appearance of understanding.

Which is exactly what happens with human evolution and development. Sure, we can say LLMs don’t have “human” understanding - which is something we can’t really define anyway - as long as we’re not trying to claim LLMs don’t have understanding at all. The latter is a much higher bar.

> We define goals that we cannot conceive of reaching without something like understanding happening.

Functionally speaking, that is understanding. Again if you want to go past a functional definition, that’s a bar which no one can clear right now.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#197

Post by exe34 »

jeremyjh wrote: post #62

These are all important points and I love the analogy. But there is an even bigger issue with having LLMs write for you: Writing is thinking. Thinking and deciding. There have been many times when I start out writing something substantial - could be an email, a blog post, a software design document, anything - when my own views substantially changed during the writing process. Writing forces you to serialize your tho…

This puts into words something I have been thinking about but haven't been able to articulate when people ask me if I'm using AI heavily. Usually when I write a report, I start out with a question and try to find some hints that will give me hypotheses that I can then test. I can't just prompt "Write me a report". The process of coming up with the information in the prompt is best done by writing the friendly report.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#198

Post by rogerrogerr »

trhaynes wrote: post #177
bcherny wrote: post #166

Earlier quoted context omitted.

(I work at Anthropic) I agree. I use an LLM to write my code, but I do all of my writing by hand, since it helps me think. It reminds me of the transition over the last year from AI-assisted coding to AI doing all the coding. At first the code output wasn't good enough, and humans read and iterated on the code all day, so the details of the source code mattered. Now, the code is largely high quality and it meets a la…

Do your coworkers send emails and create written work product using LLMs? I'm curious what the standards and culture are within an AI org.

[non-AI org] I despise this and call it out every time I see it. Some dude hooked up an LLM autoresponder to his email, sent some nauseating AI slop to a huge distribution list.

I couldn’t help myself, replied and asked him for a recipe for delicious apple cobbler and hiking trail recommendations in Glasgow, which “he” immediately provided. Highlight of my career.

I think my core argument is this: I have access to every bit of information your AI does, so if I want an AI answer I’ll get one myself. If that isn’t true, why are you hoarding information? Push it somewhere we can all see it. So the only reason I would send you a message is to access _your_ brain. I have no interest in talking to an AI through a worse interface.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#199

Post by CamperBob2 »

bcrosby95 wrote: post #180
bcherny wrote: post #166

Earlier quoted context omitted.

(I work at Anthropic) I agree. I use an LLM to write my code, but I do all of my writing by hand, since it helps me think. It reminds me of the transition over the last year from AI-assisted coding to AI doing all the coding. At first the code output wasn't good enough, and humans read and iterated on the code all day, so the details of the source code mattered. Now, the code is largely high quality and it meets a la…

You claim writing is thinking, but imply writing code isn't thinking. My opinion of LLM design review isn't that high - it seems to miss design tweaks that could vastly simplify corner cases. But if your code isn't written for human consumption maybe it doesn't matter. I'm still directly responsible for what I commit, so I can't just offload it to Claude.

I still write code, I just write it in English now. It's still rock and roll to me.

Re: Your intellectual fly is open when you use an LLM to author a post (2025)

#200

Post by jeremyjh »

a2ff6eeb0 wrote: post #193
jeremyjh wrote: post #184

Earlier quoted context omitted.

You are just talking about the output though. If you only think at a "higher level" you aren't doing the actual thinking. Its the same with code. The output may be good enough, but over time you lose touch with the details to the extent that you can no longer serve a useful steering function for the organization. Before coding agents I'd seen this with many humans when they get promoted passed the point where they wo…

Yes, of course. At some point the LLMs will also run the organization.

In the meantime, they aren't capable of doing it, and neither are humans who never understand the code.
Post reply on HN