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

GitHub Copilot: The Agent Awakens

github.blog

Post reply on HN
Print view View original

151–160 of 260 posts

Re: GitHub Copilot: The Agent Awakens

#151

Post by gopher_space »

skydhash wrote: post #122
ALittleLight wrote: post #117

Earlier quoted context omitted.

True, but if the coding becomes trivial then you'll be replaced by a good PM who can work with an agent team.

Coding was always trivial (see code generators, snippets, templates). The issue is making all the little pieces work and adjust them as needed.

No-code database work was solved with Filemaker Pro decades ago. It turned out that you also need an attention span and an interest in the subject.

Most of the flowchart automation software I've been playing around with is already good enough. The Python ecosystem is good enough. Ollama is good enough. The small, purpose built models people seem compelled to make are good enough.

If I can replicate your SaaS business model by crawling your site for a description of services, what does that do to the landscape?

Re: GitHub Copilot: The Agent Awakens

#152

Post by jetpackjoe »

phil917 wrote: post #150

I feel like anytime I try these "agentic" programming tools they always fall on their face. Devin was pretty bad and honestly soaked up more time than it saved. I've tried Cursor Composer before and came away with bad results. I tried Copilot again just now with o3-mini and it just completely hallucinated up some fields into my project when I asked it to do something... Am I taking crazy pills or do these tools kinda…

You might be asking it too much, or not giving it enough context.

I've found the Cursor Agent to work great when you give it a narrow scope and plenty of examples.

Re: GitHub Copilot: The Agent Awakens

#153

Post by throw83288 »

wholinator2 wrote: post #148
throw83288 wrote: post #115

Earlier quoted context omitted.

So Work=0.1^Ct where C is the development pace. Everything points to the C of AI being large. How quickly does Work become a rounding error? Sure, C=log(t), but it could also be C=ke^t. Everything to me feels like it's the latter, I really want to be wrong.

Cmon man, look at nature, exponential curves almost never are actually exponential. Likely it's the first part of a logistic curve. Of course you can sit here all day and cry about the worst outcome for an event in the long list of things no one can predict. It sounds like you've made your mind up anyways and refuse to listen to reason, so why keep replying to literally everyone here telling you that your buying into…

Honestly I think moving up in a layer of abstraction is not the same as something resembling an intelligent agent.

Re: GitHub Copilot: The Agent Awakens

#154

Post by skydhash »

gopher_space wrote: post #151
skydhash wrote: post #122

Earlier quoted context omitted.

Coding was always trivial (see code generators, snippets, templates). The issue is making all the little pieces work and adjust them as needed.

No-code database work was solved with Filemaker Pro decades ago. It turned out that you also need an attention span and an interest in the subject. Most of the flowchart automation software I've been playing around with is already good enough. The Python ecosystem is good enough. Ollama is good enough. The small, purpose built models people seem compelled to make are good enough. If I can replicate your SaaS business…

As always, the edge cases, which you will be aware of by talking to domain experts or the experience of managing the production services for years. There's a reason we're still running decades old software written in no longer maintained programming languages. The only valuable specs was always the code.

Re: GitHub Copilot: The Agent Awakens

#156

Post by phil917 »

jetpackjoe wrote: post #152
phil917 wrote: post #150

I feel like anytime I try these "agentic" programming tools they always fall on their face. Devin was pretty bad and honestly soaked up more time than it saved. I've tried Cursor Composer before and came away with bad results. I tried Copilot again just now with o3-mini and it just completely hallucinated up some fields into my project when I asked it to do something... Am I taking crazy pills or do these tools kinda…

You might be asking it too much, or not giving it enough context. I've found the Cursor Agent to work great when you give it a narrow scope and plenty of examples.

Perhaps, but at that point I feel like I'm spending more time feeding the tool the right prompt and context, going back and forth with corrections, etc... when I could just write the code myself with less time and hassle.

I've definitely had far more success with using AI as a fuzzy search or asking it for one-off pieces of functionality. Any time I ask it to interact directly inside my codebase, it usually fails.

Re: GitHub Copilot: The Agent Awakens

#157

Post by Degorath »

bdangubic wrote: post #116
konart wrote: post #111

Earlier quoted context omitted.

>Call me a doomsday prepper >Seems obvious that I missed the boat on LLMs. Don't worry. As the other commenter said it: we've seen it all a few times already. I clearly remember how some people reacted to Ruby on Rails as if it's going to replace them just because it provides... well a framework. LLMs won't replace even a junior dev anytime soon. Not to mention senior dev etc. People who's main job was creating landi…

LLMs won't replace even a junior dev anytime soon. Not to mention senior dev etc. except of course they have already … in many places … and counting :)

Actually curious - where have they? Zuck's claim didn't seem to be true. I'd imagine a few places that have low technical acumen have tried, but I'll want to see how much they pay for SWEs willing to clean that codebase after they let LLMs run amok on it.

Re: GitHub Copilot: The Agent Awakens

#158

Post by sangnoir »

throw83288 wrote: post #94
suyash wrote: post #55

Earlier quoted context omitted.

The irony doesn't end there, later in the post they say "We’re excited to share a first look at our autonomous SWE agent and how we envision these types of agents will fit into the GitHub user experience. When the product we are building under the codename Project Padawan ships later this year, it will allow you to directly assign issues to GitHub Copilot, using any of the GitHub clients, and have it produce fully te…

> Effectively they have completely automated SWE job, pair programmer was just a marketing speak, real intention is clear. Frankly, this was obvious to me since the Copilot Workspace announcement. It's so hard not for me to not slide completely into nihilistic despair as a student right now. I chose wrong, and now there is nothing I can do. Day in and day out I'm talking about my projects and internships as if my ent…

> Call me a doomsday prepper, but frankly I haven't heard a compelling argument against this line of thinking that is actually in line with the absurd development curve.

Are the current economics viable indefinitely? I think not. This AI investment exuberance will be curbed as soon as investors start demanding returns, and we've already seen harbingers of that (the Deep Seek market scare). What appears to be a quadratic growth curve inevitably turns out to be sigmoid.

Right now, the Hype train is at maximum speed and seems unstoppable. Despite the early hype, the Internet didn't replace colleges or brick and mortar stores[1], iPads didn't kill computers[2], and AI won't replace software engineers. This is not to say there will be no impact, but it's being oversold.

1. Khan academy and Amazon notwithstanding. But physical retail stores are still here and doing okay, and have adjusted to leveraging the new paradigm.

2. Leading up to peak iPad, it was believable that the iPad would kill PCs - it was an unstoppable juggernaut lifting Apple profits to record heights https://www.bloomberg.com/news/articles/2012-03-21/ipad-the-...

Re: GitHub Copilot: The Agent Awakens

#159

Post by mywittyname »

throw83288 wrote: post #129
mywittyname wrote: post #106

Earlier quoted context omitted.

I've been in the industry long enough to have been around for a few crashes. My outlook is: this industry has always faced threats that looked like it was going to spell the end of our careers, but we always come out the other side better than ever. I don't think LLMs are fundamentally more threatening than off shore developers were. Sure, we lost jobs during that time, but businesses realized eventually that the pro…

Your logic works for seniors, but honestly I'm unsure how it works for anybody that just wants to break in.

I was a junior after companies had already decided to out source low-level development roles. And I also faced the roadblock of lacking a degree, or any college at the time, so internships were not an option.

What I did was learn the skills that companies were hiring for and kept applying until I finally found some tiny company willing to pay me peanuts ($8.50hr, I'm not joking, I continued to work two jobs that entire year). They got a cheap worker, and I got experience that I leveraged into a better job.

How does that translate to your situation? If you're in college, find internships, it's the easiest way to get your foot in the door. Are you out of college or never went? Time to look at job postings, evaluate the skills they are looking for, and learn those skills.

Yeah, it sucks but that's also a fact of life in this industry. I have to "reskill" every few years too, because not every job I've had segues into another job. In reality, every senior developer decays over time into a junior because the tech landscape changes pretty quickly, and your choices are to mitigate that decay through learning the tech that's being hired for, or become a people manager.

I'd suggest working on your defeatest attitude though. As someone with pretty low self-esteem myself, I get it. Just four hours ago I was calling myself an idiot for making a mistake, but instead of wallowing, I took the time to "prove it" and verify that I was the root cause of the the issue. If I was, I would take those findings and learn from them, but it turns out, all I proved was that I was not responsible and I got to pat myself for building out a system that allowed me to figure this out.

You're going to have to find a way to tell yourself that you're proud of what you've done. Nobody else is going to say it. And rejection sucks. You have to learn to graciously accept rejection, and objectively look at what you've done and compliment yourself. I take the "shit sandwich approach" of finding two good things about what I've built, and one point of improvement. YMMV there, but it definitely helps with the mental health to compliment yourself when you deserve it.

Re: GitHub Copilot: The Agent Awakens

#160

Post by nprateem »

suyash wrote: post #55
diggan wrote: post #38

> When we introduced GitHub Copilot back in 2021, we had a clear goal: to make developers’ lives easier with an AI pair programmer that helps them write better code. The name reflects our belief that artificial intelligence (AI) isn’t replacing the developer. Later: > GitHub Copilot’s new agent mode is capable of iterating on its own code, recognizing errors, and fixing them automatically. Is this Microsoft/GitHub ac…

The irony doesn't end there, later in the post they say "We’re excited to share a first look at our autonomous SWE agent and how we envision these types of agents will fit into the GitHub user experience. When the product we are building under the codename Project Padawan ships later this year, it will allow you to directly assign issues to GitHub Copilot, using any of the GitHub clients, and have it produce fully te…

Cue a load of buggy code with tests modified to pass instead of fixing why tests fail.

Maybe they've just got an automatic prompt of "no dickhead fix the fucking code don't frig the tests"

Post reply on HN