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

Jules, remote coding agent from Google Labs, announces API

jules.google

Post reply on HN
Print view View original

21–30 of 81 posts

Re: Jules, remote coding agent from Google Labs, announces API

#21

Post by onion2k »

verdverm wrote: post #4

Do people trust these kinds of things to effectively work async and unsupervised? My experience with coding agents leads me to believe using something like this will end up being more noise and work than ROI I suppose it could be effectively the same loop I use in VS Code, but then why would I want an external tool over an integration?

My experience with coding agents leads me to believe using something like this will end up being more noise and work than ROI

I think that depends on how far out your horizon is. If you're only looking one task out, or maybe a few weeks out, then it's not worth investing the time yet. On the other hand, if you're looking at how your engineering team will work in 3 years time it's definitely worth starting to look at it now.

An example that comes to mind: having a bot that automatically spins up an environment when a library is updated, runs through the tests, and identifies why a codebase doesn't work with the update, and fixes it then opens an appropriate PR that passes all the tests for humans to review would be incredibly useful.

Re: Jules, remote coding agent from Google Labs, announces API

#22

Post by j_bum »

ctoth wrote: post #12
MrDarcy wrote: post #11

It’s a shame Google picked the wrong system design for Jules. Claude Code’s system design is clearly superior at this point. Jules is going to simply be another vendor locked walled garden play.

I've been using AI coding agents since the very early days of Aider and I think this is not quite true. There's a place for async agents. There's a place for collaborative agents. Collaborative agents may even soon be delegating off to multiple async agents and picking best results. There's so much complexity here and we haven't even begun to explore a corner of the possible design space. We're still trying to plug A…

Would you be willing to point me to a primer of how I can get started with building agents?

This week I experimented with building a simple planner/reviewer “agentic” iterative pipeline to automate an analysis workflow.

It was effectively me dipping my toes into this field, and I am so floored to learn more. But I’m unsure of where to start, since everything seems so fast paced.

I’m also unsure of how to experiment, since APIs rack up fees pretty quickly. Maybe local models?

Re: Jules, remote coding agent from Google Labs, announces API

#24

Post by breckenedge »

onion2k wrote: post #21
verdverm wrote: post #4

Do people trust these kinds of things to effectively work async and unsupervised? My experience with coding agents leads me to believe using something like this will end up being more noise and work than ROI I suppose it could be effectively the same loop I use in VS Code, but then why would I want an external tool over an integration?

My experience with coding agents leads me to believe using something like this will end up being more noise and work than ROI I think that depends on how far out your horizon is. If you're only looking one task out, or maybe a few weeks out, then it's not worth investing the time yet. On the other hand, if you're looking at how your engineering team will work in 3 years time it's definitely worth starting to look at…

The LLMs are a crapshoot, and probably always will be, for reliable automatic fixing of anything. They save me time 50% of the time. The other 50% they just can’t put enough together to grok what the existing code does, but damn if their code doesn’t look like it should work.

Re: Jules, remote coding agent from Google Labs, announces API

#25

Post by andrethegiant »

I am so sick of these anthropomorphized names that have nothing to do with anything that we’re all supposed to remember now. Why are we giving products first names? The worst offender is probably Amazon Rufus. It’s all so dumb and I hate it. At least attempt to be clever and name it something that relates to the product itself. Even Google Wave, despite its shortcomings, made sense as a product name.

Re: Jules, remote coding agent from Google Labs, announces API

#26

Post by yoavm »

f311a wrote: post #8
yoavm wrote: post #3

I have an old Django site I'm maintaining for a long-time customer of mine. They often want to make small changes - things that are only a few lines of code, but would take an hour to just spin up the system, remind myself how it works, commit, push, update the server and all that. Last week I've moved the whole infrastructure to Railway, and taught the customer to use Jules. They make their own PRs now, and Railway…

I hope they don't store any user data in their app. Trusting LLMs blindly is a bad idea.

Jules has access to the codebase, not the database. It doesn't see any user data.

Re: Jules, remote coding agent from Google Labs, announces API

#27

Post by yoavm »

derektank wrote: post #6
yoavm wrote: post #3

I have an old Django site I'm maintaining for a long-time customer of mine. They often want to make small changes - things that are only a few lines of code, but would take an hour to just spin up the system, remind myself how it works, commit, push, update the server and all that. Last week I've moved the whole infrastructure to Railway, and taught the customer to use Jules. They make their own PRs now, and Railway…

How expensive are the API charges? Seems like it might be a bit too easy for a customer to rack up a big bill testing out minor changes if things weren't configured correctly.

Literally free. No API - the reason I went for Jules instead of Claude Code / Gemini CLI for example is specifically because of it's relatively polished web-interface, which I assumed that my customer would appreciate. They're using their own Google account and the daily tasks free limit seem to be more than enough for them.

Re: Jules, remote coding agent from Google Labs, announces API

#28

Post by davedx »

verdverm wrote: post #4

Do people trust these kinds of things to effectively work async and unsupervised? My experience with coding agents leads me to believe using something like this will end up being more noise and work than ROI I suppose it could be effectively the same loop I use in VS Code, but then why would I want an external tool over an integration?

Yeah, in my experience you have to babysit them

Re: Jules, remote coding agent from Google Labs, announces API

#29

Post by ctoth »

j_bum wrote: post #22
ctoth wrote: post #12

Earlier quoted context omitted.

I've been using AI coding agents since the very early days of Aider and I think this is not quite true. There's a place for async agents. There's a place for collaborative agents. Collaborative agents may even soon be delegating off to multiple async agents and picking best results. There's so much complexity here and we haven't even begun to explore a corner of the possible design space. We're still trying to plug A…

Would you be willing to point me to a primer of how I can get started with building agents? This week I experimented with building a simple planner/reviewer “agentic” iterative pipeline to automate an analysis workflow. It was effectively me dipping my toes into this field, and I am so floored to learn more. But I’m unsure of where to start, since everything seems so fast paced. I’m also unsure of how to experiment,…

You can directly use Claude Code via its scriptable API (things like --verbose --output-format json --input-format json --include-partial-messages

and then use your existing Anthropic plan. Otherwise yeah you'll have to start using API tokens:

https://www.anthropic.com/engineering/building-agents-with-t...

Re: Jules, remote coding agent from Google Labs, announces API

#30

Post by bonoboTP »

yoavm wrote: post #3

I have an old Django site I'm maintaining for a long-time customer of mine. They often want to make small changes - things that are only a few lines of code, but would take an hour to just spin up the system, remind myself how it works, commit, push, update the server and all that. Last week I've moved the whole infrastructure to Railway, and taught the customer to use Jules. They make their own PRs now, and Railway…

Do they still pay you the same amount?
Post reply on HN