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

How much can you delegate to agents?

newsletter.posthog.com

Post reply on HN
Print view View original

11–20 of 24 posts

Re: How much can you delegate to agents?

#11

Post by SOLAR_FIELDS »

Frieren wrote: post #10
SOLAR_FIELDS wrote: post #9

This is a very long form way of saying “understand the work you are dispatching, and if you don’t, ask questions until you do”

> “understand the work you are dispatching, and if you don’t, ask questions until you do” My rant about this, not directed to the commenter but in general: I wish people would have been so interested on discussing and planning with teammates like they seem with AI tools. Because this is nothing new. Communication, knowing what you are doing, planning... was already a mandatory step for any engineering task. And if pe…

Dealing with humans is way harder than dealing with a machine that is programmed to agree with you

Re: How much can you delegate to agents?

#12

Post by sixtyj »

SOLAR_FIELDS wrote: post #11
Frieren wrote: post #10

Earlier quoted context omitted.

> “understand the work you are dispatching, and if you don’t, ask questions until you do” My rant about this, not directed to the commenter but in general: I wish people would have been so interested on discussing and planning with teammates like they seem with AI tools. Because this is nothing new. Communication, knowing what you are doing, planning... was already a mandatory step for any engineering task. And if pe…

Dealing with humans is way harder than dealing with a machine that is programmed to agree with you

Yes, shouting at clouds is easier with LLM :) But those clouds are deaf, sometimes.

Re: How much can you delegate to agents?

#13

Post by parasti »

This post is full of things opposite of what I've found. An agent (claude code at least) will certainly refactor feature flags better than I ever could and is less likely to miss special cases. What the agent struggles with is business knowledge - context I hold in my head as a human communicating with other humans and working on a codebase over a long period of time.

Re: How much can you delegate to agents?

#14

Post by ithkuil »

parasti wrote: post #13

This post is full of things opposite of what I've found. An agent (claude code at least) will certainly refactor feature flags better than I ever could and is less likely to miss special cases. What the agent struggles with is business knowledge - context I hold in my head as a human communicating with other humans and working on a codebase over a long period of time.

That's true. But we always desired that more business knowledge be shared in written form between humans (people come and go, work across time zones, ...).

Presumably agents can both help maintaining/mediating such communication and also benefit from the context they acquire through that

Re: How much can you delegate to agents?

#15

Post by ithkuil »

jolaflow wrote: post #3

Interesting. When it comes to auditing, I think there is also another layer to be verified - the intent. We have tooling for static analysis and automated tests, but drift in intent or vision is hard to detect. After leaving agents unsupervised for longer periods of time, the biggest questions tend to be "how did it arrive at this conclusion?" and "did we drift from the initial vision?". Typically these questions are…

I see vision drift happen routinely in most (all) human led projects.

Re: How much can you delegate to agents?

#16

Post by steve1977 »

jolaflow wrote: post #3

Interesting. When it comes to auditing, I think there is also another layer to be verified - the intent. We have tooling for static analysis and automated tests, but drift in intent or vision is hard to detect. After leaving agents unsupervised for longer periods of time, the biggest questions tend to be "how did it arrive at this conclusion?" and "did we drift from the initial vision?". Typically these questions are…

Would behaviour driven development be helpful here?

Re: How much can you delegate to agents?

#17

Post by embedding-shape »

ithkuil wrote: post #14
parasti wrote: post #13

This post is full of things opposite of what I've found. An agent (claude code at least) will certainly refactor feature flags better than I ever could and is less likely to miss special cases. What the agent struggles with is business knowledge - context I hold in my head as a human communicating with other humans and working on a codebase over a long period of time.

That's true. But we always desired that more business knowledge be shared in written form between humans (people come and go, work across time zones, ...). Presumably agents can both help maintaining/mediating such communication and also benefit from the context they acquire through that

> Presumably agents can both help maintaining/mediating such communication

What happens in practice, is that people use agents to write such communication down, don't review it, and then the wrong information persists, and future agents will regurgitate it, until it reaches a human who already know it's wrong who then goes "Huh, where did this come from?".

Re: How much can you delegate to agents?

#18

Post by jolaflow »

steve1977 wrote: post #16
jolaflow wrote: post #3

Interesting. When it comes to auditing, I think there is also another layer to be verified - the intent. We have tooling for static analysis and automated tests, but drift in intent or vision is hard to detect. After leaving agents unsupervised for longer periods of time, the biggest questions tend to be "how did it arrive at this conclusion?" and "did we drift from the initial vision?". Typically these questions are…

Would behaviour driven development be helpful here?

I think behavior driven development probably can make intent more explicit and standardized. However, I think they operate at different levels, or on a different axis if you will. BDD helps make each point in time easier to reason about wile being able to traverse the time axis helps understand how the workflow evolved.

Re: How much can you delegate to agents?

#20

Post by jolaflow »

ithkuil wrote: post #15
jolaflow wrote: post #3

Interesting. When it comes to auditing, I think there is also another layer to be verified - the intent. We have tooling for static analysis and automated tests, but drift in intent or vision is hard to detect. After leaving agents unsupervised for longer periods of time, the biggest questions tend to be "how did it arrive at this conclusion?" and "did we drift from the initial vision?". Typically these questions are…

I see vision drift happen routinely in most (all) human led projects.

That is also very true, and I think time-travel capabilities would help detect that too.
Post reply on HN