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

Building better AI tools

hazelweakly.me

Post reply on HN
Print view View original

171–180 of 189 posts

Re: Building better AI tools

#171

Post by TimPC »

tptacek wrote: post #54

This is a confusing piece. A lot of it would make sense if Weakly was talking about a coding agent (a particular flavor of agent that worked more like how antirez just said he prefers coding with AI in 2025 --- more manual, more advisory, less do-ing). But she's not: she's talking about agents that assist in investigating and resolving operations incidents. The fulcrum of Weakly's argument is that agents should stay…

I think the problem is do you want to give the AI access to prod. See the recent example where AI wiped a DB despite instructions not to (because AI sometimes does things more often when you tell it not to do something because the negative from not is not always reliably picked up)

Re: Building better AI tools

#172

Post by bluefirebrand »

danielbln wrote: post #158
bluefirebrand wrote: post #84

Earlier quoted context omitted.

Unfortunately a lot of people are basically just hoping that by the time the big bill is due, they have cashed out and left the bill on someone else I also think that even with expertise, people relying too much on AI are going to erode their expertise If you can lift heavy weights, but start to use machines to lift instead, your muscles will shrink and you won't be able to lift as much The brain is a muscle it must…

We are in the business of automation, this is also automation. What good is doing the manual work if automation provides good enough results. I increasingly consider the code an implementation detail and spend most of my thinking one abstraction level higher. It's not always there yet but it's really often good enough to great, given the right oversight.

Code is not just an implementation detail, I wish people would knock it off with that idea

It would be like saying "roofs are just an implementation detail of building a house". Fine, but you build the roof wrong your house is going to suck

Re: Building better AI tools

#173

Post by danielbln »

bluefirebrand wrote: post #172
danielbln wrote: post #158

Earlier quoted context omitted.

We are in the business of automation, this is also automation. What good is doing the manual work if automation provides good enough results. I increasingly consider the code an implementation detail and spend most of my thinking one abstraction level higher. It's not always there yet but it's really often good enough to great, given the right oversight.

Code is not just an implementation detail, I wish people would knock it off with that idea It would be like saying "roofs are just an implementation detail of building a house". Fine, but you build the roof wrong your house is going to suck

I'm tasking a contractor to lay the roof tiles and just give them my specifications. How they lay the tiles, I don't care, as long as it passes inspection afterwards and conforms to my spec.

Re: Building better AI tools

#174

Post by jgon »

bubblyworld wrote: post #160
ofjcihen wrote: post #141

Earlier quoted context omitted.

[flagged]

Let's not do this kind of thing here? There's plenty to engage with in their comments without resorting to ad-hominems or similar. (your comment is pretty mild, I'm just worried about the general trend on HN)

It's not an ad-hominem. When people are talking their book, you should know that they're talking their book, and that knowledge doesn't have to negate any sound points they're making or cause you to disregard everything they're saying, it just colors your evaluation of their arguments, as it should. I don't think this is controversial, and seeing that comment flagged is pretty disheartening, adding context is almost never a bad thing.

Re: Building better AI tools

#175

Post by tptacek »

jgon wrote: post #174
bubblyworld wrote: post #160

Earlier quoted context omitted.

Let's not do this kind of thing here? There's plenty to engage with in their comments without resorting to ad-hominems or similar. (your comment is pretty mild, I'm just worried about the general trend on HN)

It's not an ad-hominem. When people are talking their book, you should know that they're talking their book, and that knowledge doesn't have to negate any sound points they're making or cause you to disregard everything they're saying, it just colors your evaluation of their arguments, as it should. I don't think this is controversial, and seeing that comment flagged is pretty disheartening, adding context is almost…

I don't care, in part because the claim is false, but there's literally a guideline saying you can't do this, so I guess it's worth knowing that you're wrong too.

Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.

Re: Building better AI tools

#176

Post by ofjcihen »

tptacek wrote: post #175
jgon wrote: post #174

Earlier quoted context omitted.

It's not an ad-hominem. When people are talking their book, you should know that they're talking their book, and that knowledge doesn't have to negate any sound points they're making or cause you to disregard everything they're saying, it just colors your evaluation of their arguments, as it should. I don't think this is controversial, and seeing that comment flagged is pretty disheartening, adding context is almost…

I don't care, in part because the claim is false, but there's literally a guideline saying you can't do this, so I guess it's worth knowing that you're wrong too. Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.

In this case it’s relevant to the discussion as the user was questioning why you were making the points you were.

It’s not an accusation of shilling, it’s context where context was requested.

As a test imagine if you changed the context to something good such as “AI achieves the unthinkable” and the responding user asked why someone was so optimistic about the achievement.

It’s relevant context to the conversation, nothing else.

Re: Building better AI tools

#177

Post by ofjcihen »

jgon wrote: post #174
bubblyworld wrote: post #160

Earlier quoted context omitted.

Let's not do this kind of thing here? There's plenty to engage with in their comments without resorting to ad-hominems or similar. (your comment is pretty mild, I'm just worried about the general trend on HN)

It's not an ad-hominem. When people are talking their book, you should know that they're talking their book, and that knowledge doesn't have to negate any sound points they're making or cause you to disregard everything they're saying, it just colors your evaluation of their arguments, as it should. I don't think this is controversial, and seeing that comment flagged is pretty disheartening, adding context is almost…

I appreciate this response and I’m also as confused as you are. It’s information relevant to the conversation, not an accusation (it would be an odd accusation to make, no?)

Re: Building better AI tools

#178

Post by otterley »

tptacek wrote: post #54

This is a confusing piece. A lot of it would make sense if Weakly was talking about a coding agent (a particular flavor of agent that worked more like how antirez just said he prefers coding with AI in 2025 --- more manual, more advisory, less do-ing). But she's not: she's talking about agents that assist in investigating and resolving operations incidents. The fulcrum of Weakly's argument is that agents should stay…

> There are actions AI tools shouldn't perform autonomously (I certainly wouldn't let one run a Terraform apply), but there are plenty of actions where it doesn't make sense to stop them.

I'm curious as to where you would draw the line. Assuming you've adhered to DevOps best practices, most--if not all--changes would require some sort of code commit and promotion through successive environments to reach production. This isn't just application code, of course; it's also your infrastructure. In such a situation, what would you permit an agent to autonomously perform in the course of incident resolution?

Re: Building better AI tools

#179

Post by bubblyworld »

jgon wrote: post #174
bubblyworld wrote: post #160

Earlier quoted context omitted.

Let's not do this kind of thing here? There's plenty to engage with in their comments without resorting to ad-hominems or similar. (your comment is pretty mild, I'm just worried about the general trend on HN)

It's not an ad-hominem. When people are talking their book, you should know that they're talking their book, and that knowledge doesn't have to negate any sound points they're making or cause you to disregard everything they're saying, it just colors your evaluation of their arguments, as it should. I don't think this is controversial, and seeing that comment flagged is pretty disheartening, adding context is almost…

It is quite literally an ad-hominem, in that it is aimed at the person, not the argument. The issue isn't that more context is bad (I agree with you, it's useful), it's that as a policy for a discussion board I think allowing this kind of thing is a bad idea. People can be mistaken, or lie, and comments get ugly fast when it's personal. Not to mention the fine line between this and doxxing.

(e.g. here, the OP has claimed that they do not in fact have a vested interest in AI - so was this "context" really a good thing?)

Re: Building better AI tools

#180

Post by tptacek »

ofjcihen wrote: post #176
tptacek wrote: post #175

Earlier quoted context omitted.

I don't care, in part because the claim is false, but there's literally a guideline saying you can't do this, so I guess it's worth knowing that you're wrong too. Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.

In this case it’s relevant to the discussion as the user was questioning why you were making the points you were. It’s not an accusation of shilling, it’s context where context was requested. As a test imagine if you changed the context to something good such as “AI achieves the unthinkable” and the responding user asked why someone was so optimistic about the achievement. It’s relevant context to the conversation, n…

It's false context meant to impeach my arguments. Not a close call.
Post reply on HN