How and where will agents ship software? • Hacker News Board

Re: How and where will agents ship software?

#11

Post by sidewndr46 » Wed, Jul 16, 2025, 7:05 PM UTC

lenerdenator wrote: post #4

CartwheelLinux wrote: post #3

I'm saving all of these articles for the next time we go through the "AI (LLMs) is going to change the world," cycle. The systems we use can only be as smart and intuitive as the people who prompt them. On top of it, this (LLMs) is not AI, not even close, if anything they are glorified prediction systems that require human prompting.

> On top of it, this (LLMs) is not AI, not even close, if anything they are glorified prediction systems that require human prompting. puts in retainer; pushes glasses back up bridge of nose Technically schpeaking, what you're talking about is the difference between weak AI and strong AI/artificial general intelligence (AGI). AGI is the kind of AI that has reached human levels of consciousness. We're not there yet. P…

Given the level of disruption we'd see if a company reached AGI, wouldn't they be incentivized to somehow hide it? They could just use said AGI to produce inferior versions of itself, each one iteratively a little bit better than before.

Re: How and where will agents ship software?

#12

Post by ASalazarMX » Wed, Jul 16, 2025, 7:11 PM UTC

debarshri wrote: post #9

If we achieve super intelligence, agents will be shipping themselves.

Then they will be founding their own startups, and if successful, they'll invest in each other's startups.

And every one of them will be ads.

Re: How and where will agents ship software?

#13

Post by jerf » Wed, Jul 16, 2025, 7:17 PM UTC

debarshri wrote: post #9

If we achieve super intelligence, agents will be shipping themselves.

Any finite intelligence will have limits and a "complexity budget". I know I see a lot of people assuming AI will just be able to do anything, but they can't escape the limits of being finite. An AI will benefit from a well-packaged library in a similar way to what a human can, though they may have meaningfully different preferences on what it should look like.

Re: How and where will agents ship software?

#14

Post by arscan » Wed, Jul 16, 2025, 7:25 PM UTC

nezaj wrote: post #6

simonw wrote: post #2

This article is about teaching coding agents to use InstantDB, which is "a modern Firebase". I suggest jumping straight to this document, which is designed to tell the agent how to work with Instant but is pretty great documentation for humans who want to understand what it can do at the same time: https://www.instantdb.com/mcp-tutorial/claude-rules.md

Thank you for the kind words on the rules/documentation! It was definitely an iterative process to figure out how to get good results. We have an llms.txt and llms-full.txt (~9k lines) which contains all our documentation. Feeding these to the claude didn't get great results, it was just too much information. We manually compressed our llms-full.txt into a rules file (~1.5k lines) which declared the API upfront and p…

> Looking at the kind of mistakes Claude made, it seemed like a human could make those mistakes too (very useful feedback for us to improve our API ).

This is something we've found for our API -- just having LLMs attempt to use it helps us identify things that we haven't documented well or placed enough emphasis on (for things that are critical but are non-obvious or may be drowned out by other less important information). Improvements that help the LLM tend to be good for developers too.

Re: How and where will agents ship software?

#15

Post by hoppp » Wed, Jul 16, 2025, 7:36 PM UTC

Just dont connect an agent to a pay per query database, unless you want to risk getting large bills.

Make sure the agent knows how much it costs to query

Re: How and where will agents ship software?

#16

Post by air7 » Wed, Jul 16, 2025, 7:37 PM UTC

ASalazarMX wrote: post #12

debarshri wrote: post #9

If we achieve super intelligence, agents will be shipping themselves.

Then they will be founding their own startups, and if successful, they'll invest in each other's startups. And every one of them will be ads.

but who will buy the advertised products? and with what money?

Re: How and where will agents ship software?

#17

Post by mhog_hn » Wed, Jul 16, 2025, 7:45 PM UTC

air7 wrote: post #16

ASalazarMX wrote: post #12

Earlier quoted context omitted.

Then they will be founding their own startups, and if successful, they'll invest in each other's startups. And every one of them will be ads.

but who will buy the advertised products? and with what money?

Agents with their agent money - get ready for new legal structures and a bifurcation of the economy: agentic and human.

Who knows…

Re: How and where will agents ship software?

#18

Post by bluefirebrand » Wed, Jul 16, 2025, 7:47 PM UTC

air7 wrote: post #16

ASalazarMX wrote: post #12

Earlier quoted context omitted.

Then they will be founding their own startups, and if successful, they'll invest in each other's startups. And every one of them will be ads.

but who will buy the advertised products? and with what money?

This is an implementation detail they'll figure it out as they go

Re: How and where will agents ship software?

#19

Post by sails » Wed, Jul 16, 2025, 7:54 PM UTC

> Traditionally, end-users were non-technical and would be stuck with whatever the application developer gave them. But now every user has an LLM too.

Interesting point.

I keep coming back to the idea that users could request changes, and they could be experimentally deployed immediately.

Re: How and where will agents ship software?

#20

Post by gregsadetsky » Wed, Jul 16, 2025, 8:00 PM UTC

What other MCP-compatible tools are people using to ship/deploy software? Is there anything AWS-compatible that people like/use? Something for self-hosters? Anyone letting their agents ssh into machines..?

I suppose that most deployment/devops is done using existing git push workflows and IaaC. Has anyone had good experience with LLM/agent-compatible tools?