Building better AI tools

#1

Post by eternalreturn » Wed, Jul 23, 2025, 2:56 PM UTC

Re: Building better AI tools

#2

Post by askafriend » Wed, Jul 23, 2025, 3:17 PM UTC

While I understand the author's point, IMO we're unlikely to do anything that results in slowing down first. Especially in a competitive, corporate context that involves building software.

Re: Building better AI tools

#3

Post by journal » Wed, Jul 23, 2025, 3:26 PM UTC

Creating these or similar things requires individual initiative but the whole world everywhere with money is run by a committee with shared responsibility where no one will be held responsible if the project fails. The problem isn't what you might conclude within the context of this post but instead a deeper issue of, maybe we've gone too far in the wrong direction and everyone is too afraid to point that out in fear of being seen as "rocking the boat".

Re: Building better AI tools

#4

Post by Edmond » Wed, Jul 23, 2025, 3:30 PM UTC

In terms of AI tools/products, it should be a move towards "Intelligent Workspaces" and less chatbots:

https://news.ycombinator.com/item?id=44627910

Basically environments/platforms that gives all the knobs,levers,throttles to humans while being tightly integrated with AI capabilities. This is hard work that goes far beyond a VSCode fork.

Re: Building better AI tools

#5

Post by datadrivenangel » Wed, Jul 23, 2025, 3:30 PM UTC

Author makes some good points about designing human computer interfaces, but has a very opinionated view of how AI can be used in systems engineering tooling which seems like it misses a lot of places where AI can be useful even without humans in the loop?

Re: Building better AI tools

#6

Post by pplonski86 » Wed, Jul 23, 2025, 3:35 PM UTC

Edmond wrote: post #4

In terms of AI tools/products, it should be a move towards "Intelligent Workspaces" and less chatbots: https://news.ycombinator.com/item?id=44627910 Basically environments/platforms that gives all the knobs,levers,throttles to humans while being tightly integrated with AI capabilities. This is hard work that goes far beyond a VSCode fork.

It is much easier to implement chat bot that intelligent workspace, and AI many times doesn't need human interaction in the loop.

I would love to see other interfaces other than chats for interacting with AI.

Re: Building better AI tools

#7

Post by swiftcoder » Wed, Jul 23, 2025, 3:36 PM UTC

datadrivenangel wrote: post #5

Author makes some good points about designing human computer interfaces, but has a very opinionated view of how AI can be used in systems engineering tooling which seems like it misses a lot of places where AI can be useful even without humans in the loop?

The scenarios in the article are all about mission-critical disaster recovery - we don't even trust the majority of our human colleagues with those scenarios! AI won't make inroads there without humans in the loop, until AI is 100% trustworthy.

Re: Building better AI tools

#8

Post by nico » Wed, Jul 23, 2025, 3:41 PM UTC

Edmond wrote: post #4

In terms of AI tools/products, it should be a move towards "Intelligent Workspaces" and less chatbots: https://news.ycombinator.com/item?id=44627910 Basically environments/platforms that gives all the knobs,levers,throttles to humans while being tightly integrated with AI capabilities. This is hard work that goes far beyond a VSCode fork.

Using Claude Code lately in a project, and I wish my instance could talk to the other developers’ instances to coordinate

I know that we can modify CLAUDE.md and maintain that as well as docs. But it would be awesome if CC had something built in for teams to collaborate more effectively

Suggestions are welcomed

Re: Building better AI tools

#9

Post by datadrivenangel » Wed, Jul 23, 2025, 3:43 PM UTC

swiftcoder wrote: post #7

datadrivenangel wrote: post #5

Author makes some good points about designing human computer interfaces, but has a very opinionated view of how AI can be used in systems engineering tooling which seems like it misses a lot of places where AI can be useful even without humans in the loop?

The scenarios in the article are all about mission-critical disaster recovery - we don't even trust the majority of our human colleagues with those scenarios! AI won't make inroads there without humans in the loop, until AI is 100% trustworthy.

And the author assumes that these humans are going to be very rigorous, which is good for SRE teams, but even then not consistently.

Re: Building better AI tools

#10

Post by qsort » Wed, Jul 23, 2025, 3:47 PM UTC

nico wrote: post #8

Edmond wrote: post #4

In terms of AI tools/products, it should be a move towards "Intelligent Workspaces" and less chatbots: https://news.ycombinator.com/item?id=44627910 Basically environments/platforms that gives all the knobs,levers,throttles to humans while being tightly integrated with AI capabilities. This is hard work that goes far beyond a VSCode fork.

Using Claude Code lately in a project, and I wish my instance could talk to the other developers’ instances to coordinate I know that we can modify CLAUDE.md and maintain that as well as docs. But it would be awesome if CC had something built in for teams to collaborate more effectively Suggestions are welcomed

This is interesting but I'm not sure I'd want it as a default behavior. Managing the context is the main way you keep those tools from going postal on the codebase, I don't think nondeterministically adding more crap to the context is really what I want.

Perhaps it could be implemented as a tool? I mean a pair of functions:

  PushTeamContext()
  PullTeamContext()

that the agent can call, backed by some pub/sub mechanism. It seems very complicated and I'm not sure we'd gain that much to be honest.