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

Jules: An asynchronous coding agent

jules.google

Post reply on HN
Print view View original

151–160 of 245 posts

Re: Jules: An asynchronous coding agent

#151

Post by mark_l_watson »

jspdown wrote: post #113

> Jules creates a PR of the changes. Approve the PR, merge it to your branch, and publish it on GitHub. Then, who is testing the change? Even for a dependency update with a good test coverage, I would still test the change. What takes time when uploading dependencies is not the number of line typed but the time it takes to review the new version and test the output. I'm worried that agent like that will promote bad p…

It shows you code diffs, results of executing modified or new code in a VPS, and it writes pull requests, but asks you to hit the Merge button in GitHub.

Will this promote bad practice? Probably up to the individual practitioner or organization.

Re: Jules: An asynchronous coding agent

#152

Post by bendigedig »

netdevphoenix wrote: post #149
disqard wrote: post #103

Earlier quoted context omitted.

Shhhh... don't tell the plebes what it really means to "2x their productivity". Seriously though, this kind of tech-assisted work output improvement has happened many times in the past, and by now we should all have been working 4-hour weeks, but we all know how it has actually worked out.

As a business owner, why would give up some of the profits? You started a business to make money not to do charity. Expecting businesses to act against their interests make no sense

This is the kind of attitude that leads to revolutions.

Re: Jules: An asynchronous coding agent

#153

Post by jacob019 »

seunosewa wrote: post #132
jacob019 wrote: post #72

Earlier quoted context omitted.

It's actually a decent patern for agents. I wrote a pricing system with an anylyst agent, a decision agent, and a review agent. They work together to make decisions that comply with policy. It's funny to watch them chatter sometimes, they really play their role, if the decision agent asks the anylyst for policy guidance it refuses and explains that it's role is to analyze. Though they do often catch mistakes that way…

Is the code available?

I had not thought about sharing it. I rolled my own framework, even though there are several good choices. I'd have to tidy it up, but would consider it if a few people ask. Shoot me an email, info in my profile.

The more difficult part which I won't share was aggregating data from various systems with ETL scripts into a new db that I generate various views with, to look at the data by channel, timescale, price regime, cost trends, inventory trends, etc. A well structured JSON object is passed to the analyst agent who prepares a report for the decision agent. It's a lot of data to analyze. It's been running for about a month and sometimes I doubt the choices, so I go review the thought traces, and usually they are right after all. It's much better than all the heuristics I've used over the years.

I've started using agents for things all over my codebase, most are much simpler. Earlier use of LLM's might have been called that in some cases, before the phrase became so popular. As everyone is discovering, it's really powerful to abstract the models with a job hat and structured data.

Re: Jules: An asynchronous coding agent

#154

Post by vincnetas »

yard2010 wrote: post #127
CobrastanJorji wrote: post #69

So, you can assign github issues to this thing, and it can handle them, merge the results in, and mark the bug as fixed? I kind of wonder what would happen if you added a "lead dev" AI that wrote up bugs, assigned them out, and "reviewed" the work. Then you'd add a "boss" AI that made new feature demands of the lead dev AI. Maybe the boss AI could run the program and inspect the experience in some way so it could dem…

Please stop this train! I want to get off

You can get off anytime you want. But train will not wait for you :(

Re: Jules: An asynchronous coding agent

#155

Post by vincnetas »

kristopolous wrote: post #119
diggan wrote: post #16

Earlier quoted context omitted.

> Google’s ability to offer inference for free is a massive competitive advantage vs everyone else: Haven't tried Jules myself yet, still playing around with Codex, but personally I don't really care if it's free or not. If it solves my problems better than the others, then I'll use it, otherwise I'll use other things. I'm sure I'm not alone in focusing on how well it works, rather than what it costs (until a certain…

$0 opens up new doors. You use it differently at $0. Fundamentally.

until you built your stuff on 0$ assumption start depending on it and then the price increases.

Re: Jules: An asynchronous coding agent

#156

Post by risyachka »

robofanatic wrote: post #76
CobrastanJorji wrote: post #69

So, you can assign github issues to this thing, and it can handle them, merge the results in, and mark the bug as fixed? I kind of wonder what would happen if you added a "lead dev" AI that wrote up bugs, assigned them out, and "reviewed" the work. Then you'd add a "boss" AI that made new feature demands of the lead dev AI. Maybe the boss AI could run the program and inspect the experience in some way so it could dem…

seems like the 1 person unicorn will be a reality soon :-)

Doesn't seem likely. If tools allow a single person to create a full-fledged product and support it etc - millions of those will pop up over night.

Thats the issue with AI - it doesn't give you any competitive advantage as everyone has it == no one has it. The entry bar is so low kids can do it.

Re: Jules: An asynchronous coding agent

#157

Post by tgtweak »

jacob019 wrote: post #72
CobrastanJorji wrote: post #69

So, you can assign github issues to this thing, and it can handle them, merge the results in, and mark the bug as fixed? I kind of wonder what would happen if you added a "lead dev" AI that wrote up bugs, assigned them out, and "reviewed" the work. Then you'd add a "boss" AI that made new feature demands of the lead dev AI. Maybe the boss AI could run the program and inspect the experience in some way so it could dem…

It's actually a decent patern for agents. I wrote a pricing system with an anylyst agent, a decision agent, and a review agent. They work together to make decisions that comply with policy. It's funny to watch them chatter sometimes, they really play their role, if the decision agent asks the anylyst for policy guidance it refuses and explains that it's role is to analyze. Though they do often catch mistakes that way…

What tooling did you use to make the agents cross-collaborate?

Re: Jules: An asynchronous coding agent

#159

Post by m3kw9 »

CobrastanJorji wrote: post #69

So, you can assign github issues to this thing, and it can handle them, merge the results in, and mark the bug as fixed? I kind of wonder what would happen if you added a "lead dev" AI that wrote up bugs, assigned them out, and "reviewed" the work. Then you'd add a "boss" AI that made new feature demands of the lead dev AI. Maybe the boss AI could run the program and inspect the experience in some way so it could dem…

I feel you are one hallucination from a big branch of issues needing to be reversed and a lot of tokens wasted

Re: Jules: An asynchronous coding agent

#160

Post by hnlurker22 »

I decided to be an engineer as opposed to manager because I didn't like people management. Now it looks like I'm forced to manage robots that talk like people. At least I can be the as non-empathetic as I want to be. Unless a startup starts doing HR for AI agents then I'm screwed.
Post reply on HN