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

The Eternal Sloptember

geohot.github.io

Post reply on HN
Print view View original

111–120 of 389 posts

Re: The Eternal Sloptember

#111

Post by cwillu »

asixicle wrote: post #98
thedjpetersen wrote: post #54

Part of my job is working on trying to make these models productive for the large corporation I work for. It's a lot of throwing tomatoes at a wall and to a degree I see the issue he is talking about output seemingly having a certain ceiling. At the same time in no part of his post is any code snippet or anything to latch on to of "the model performed poorly here when it should have done this" - this style of critici…

This is an excellent point, and as a novice using LLMs for projects I could never previously dream of doing I find myself looking for the same, examples or citations of what exactly agents are writing incorrectly and how would the human do it better. I'm sure they're out there, maybe someone can refer some good content showing such examples. I have no doubt the top nth percent of coders could write circles around Cla…

The problem is what they do to large existing systems: subtle misunderstandings mean subtle bugs are constantly being introduced, and very few shops have adequate systems in place to receive reports of subtle issues at the rates they occurred 10 years ago, let alone today. And don't even get me started on llm-assisted support that some might suggest as a solution.

Re: The Eternal Sloptember

#112

Post by bluegatty »

jofzar wrote: post #57
farhanhubble wrote: post #14

I'm in the "haven't written any code in a while" boat ATM. I'd love to see examples of issues that are so big that they warrant reverting to manual coding. My main issue has been the inconsistent quality across between model releases and the tendency to insert older APIs or documentation, especially with command line tools. I can understand if the model struggles with a million line monolithic codebase with a decade…

> I'd love to see examples of issues that are so big that they warrant reverting to manual coding Ah I see your org hasnt yet had an outage caused by a bad LLM code push.

"Ah I see your org hasnt yet had an outage caused by a bad LLM code push"

"We went back to shovelling by hand because someone ran over the pole with the front-loader, even though he had no experience driving it."

This is definitely user error; obviously it's a hard tool to wrangle but it's entirely possible to use it safely.

Re: The Eternal Sloptember

#113

Post by Alex_L_Wood »

altcognito wrote: post #25
spiderfarmer wrote: post #11

Coders underestimate the utility of AI in so many boring day to day tasks. If you freelance, that’s where the money is at, not in creating a startup that fills holes in AI offerings or in creating generic slop while hoping for ad money.

The amount of domain specific apps that will be created will likely make excel look like yesterday’s news.

I heard that a year ago, I guess we still need to wait a bit more. Thought agents were fast!

Re: The Eternal Sloptember

#114

Post by peteforde »

asixicle wrote: post #98
thedjpetersen wrote: post #54

Part of my job is working on trying to make these models productive for the large corporation I work for. It's a lot of throwing tomatoes at a wall and to a degree I see the issue he is talking about output seemingly having a certain ceiling. At the same time in no part of his post is any code snippet or anything to latch on to of "the model performed poorly here when it should have done this" - this style of critici…

This is an excellent point, and as a novice using LLMs for projects I could never previously dream of doing I find myself looking for the same, examples or citations of what exactly agents are writing incorrectly and how would the human do it better. I'm sure they're out there, maybe someone can refer some good content showing such examples. I have no doubt the top nth percent of coders could write circles around Cla…

Reality: the top nth percent of coders are seeing absurd, dramatic gains in productivity using LLMs. See: antirez, Simon Willison, Steve Yegge.

The more experience you bring to the table, the more value you get from these tools.

Look, about 12 years ago articles about how if you're not pair programming you're doing it wrong were on HN's home page every day. Doing well prompted plan -> agent -> debug cycles is like pair programming with someone that knows every SDK and API intuitively and doesn't have to pick up their kids from daycare at 4pm.

Re: The Eternal Sloptember

#115

Post by forgetfreeman »

ares623 wrote: post #18
mountainriver wrote: post #4

My guess is the models just continue to get better and better When I got into agentic coding a year or two ago I was sure it was only good at autocomplete. Something happened earlier this year where the models hit a new level of capability. Everyone I know now just does agentic coding, and it’s really amazing. I think we should just try pushing this as far as we can possibly go, it really feels like the acceleration…

what if we're accelerating to a brick wall?

More like neo-feudalism by way of breadlines.

Re: The Eternal Sloptember

#116

Post by bluegatty »

siriusastrebe wrote: post #96
bluegatty wrote: post #52

Earlier quoted context omitted.

At a granular level, it's almost guaranteed that you cannot write better code than an agent. Agents now are writing extremely consistent, normalized canonical code, that usually compiles the first time. Right out of the 'textbook'. For what it's trying to do - it writes nearly perfect code. The only thing you could nominally disagree with are some of the conventions and idioms. It 'writes a perfect novel, in perfect…

I don't think LLMs inherently do anything perfectly. They can make sure it compiles and passes tests and they can be trained to do an enormous array of tasks, but the code it generates isn't perfect, it's selecting one of many possible outputs based off of some numbers it came up with after a few matrix multiplications and ReLU activations. Those matrix multiplications aren't a divine perfect thing. They suffer from…

"Those matrix multiplications aren't a divine perfect thing. They suffer from floating point precision issues " - this is not the right intuition.

"Not by our human definition of perfect."?

'Human definition' has nothing to do with it.

Your job is to define what you want, to the extent you can do that, the AI does really well at a certain scale, at the 'functional' scale, nearly perfectly.

Re: The Eternal Sloptember

#117

Post by theojulienne »

c0rruptbytes wrote: post #88
jofzar wrote: post #57

Earlier quoted context omitted.

> I'd love to see examples of issues that are so big that they warrant reverting to manual coding Ah I see your org hasnt yet had an outage caused by a bad LLM code push.

sounds like bad deployment practices - canaries, guardrails, fast rollbacks, ring based promotions, cell based architecture, blah blah etc... humans write bad code too, there should be systems in place to protect it from releasing

I think people spend way too much time trying to say that LLMs are bad / shouldn't be used / etc because the LLM can't get it right the first time and/or makes mistakes. I think this is because we all hope that software/computers work like this in an ideal world, and LLMs are software.

This is the wrong mental model.

The way to think about an LLM is like a human: prone to following bad examples if it sees them, needs guardrails to catch mistakes, needs code review. It also needs access to what "correct" looks like: architectural design documents, skills that explain each type of change, etc. It needs prompting/skills telling it to follow a safe workflow, telling it to consider how a safe rollout would work, what a safe rollback would look like, what the performance implications are - just like a human.

The nice thing is that you now have a very knowledgable assistant that can help write additional guardrails that would have always ended at the bottom of your backlog. Perhaps it used to take many hours to research and understand how to write a custom linter to catch a specific coding pattern. Today, ask Claude to do it and an hour later you'll have a custom linter rule for your language of choice, guaranteeing the same mistake can't happen again because CI will block it.

Re: The Eternal Sloptember

#118

Post by marcus_holmes »

tra3 wrote: post #21
farhanhubble wrote: post #14

I'm in the "haven't written any code in a while" boat ATM. I'd love to see examples of issues that are so big that they warrant reverting to manual coding. My main issue has been the inconsistent quality across between model releases and the tendency to insert older APIs or documentation, especially with command line tools. I can understand if the model struggles with a million line monolithic codebase with a decade…

When every prompt produces a thousand line PR, you’re not very far from another million line monolith. I’m a little more hopeful than the author though. I feel like it’s possible to manage the process so that does not happen.

> manage the process so that does not happen

This is the gold, right here.

It doesn't engineer. It writes code. Enthusiastically. Usually without thinking about the bigger picture, the design, the architecture, the trade-offs, etc.

It's up to us to manage that process.

It's why senior engineers are finding LLMs a really useful tool - because we've learned to think about all that other stuff before opening the text editor. Writing the actual code was always the easy (and least valuable) bit.

Re: The Eternal Sloptember

#119

Post by somewhatgoated »

aeve890 wrote: post #33
mountainriver wrote: post #4

My guess is the models just continue to get better and better When I got into agentic coding a year or two ago I was sure it was only good at autocomplete. Something happened earlier this year where the models hit a new level of capability. Everyone I know now just does agentic coding, and it’s really amazing. I think we should just try pushing this as far as we can possibly go, it really feels like the acceleration…

>... I was sure it was only good at autocomplete. Something happened earlier this year where the models hit a new level of capability. Yes, something happened, it got better at autocomplete. What else could be? The underlying model hasn't changed. >acceleration of the human race Please just stop with this bullshit. Nobody's curing cancer, climate change, inequality or whatever important real problem there is with LLM…

I’m sure I would be just as useless as an LLM in the “niche stack” examples that you cited.

Why do you think that is actually a good argument against? Most “business” problems have already been solved in some way and the times I had to write really novel code in my career have been very very few.

Also sure LLMs haven’t solved cancer or unequality in the few years they exist - but humans also failed here in the last couple thousand

Re: The Eternal Sloptember

#120

Post by oneeyedpigeon »

albinn wrote: post #100

> It’s definitely a better Google for most searches I can't agree with this. You tend to get one point of view, often without any actual resources and references so you have to go look it up yourself, on [insert search engine]. Plus, what does it say when we consider an AI the one stop for our data intakes.

I find that it's typically better than Google search has been for a while, but not better than it's ever been.
Post reply on HN