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

251–260 of 260 posts

Re: GitHub Copilot: The Agent Awakens

#251

Post by throw83288 »

mhnthrow wrote: post #244
throw83288 wrote: post #145

Earlier quoted context omitted.

I dunno, a job? I don't think one other person's idea is enough. > ideas are everywhere, they are cheap. the idea plus the execution, timing, marketing, and approach are all factors in something being successful And water is everywhere but you need a boat to get across it. I don't think I have a boat. I don't know if I can build one. I don't know if anyone will let me on their boat. s/boat/idea generation/g.

can you describe how any idea of this form connects to a job? I think what I'm saying is you don't need any "idea" - it's enough to have skills. You might be overestimating the bar you need to it or what it takes to get jobs in general.

The only thing I think that makes my resume as a student appealing is having real-world projects that show I can meaningfully develop. I'd need similar for GenAI, I'd imagine.

Re: GitHub Copilot: The Agent Awakens

#252

Post by blah2244 »

mohsen1 wrote: post #232
simonw wrote: post #79

Earlier quoted context omitted.

I answer those kinds of questions by piping my entire codebase into a large context model (like Claude or o3-mini or Gemini) and prompting it directly. Here's a recent example: files-to-prompt datasette tests -e py -c | \ llm -m gemini-2.0-flash-exp -u \ 'which of these files contain tests that indirectly exercise the label_column_for_table() function' https://gist.github.com/simonw/bee455c41d463abc6282a5c9c132c...

https://github.com/bodo-run/yek This is more sophisticated for serializing your repo. Please check it out and let me know what do you think?

Yek is fantastic -- I've converted my whole team to using it for prompting. As input context windows keep increasing, I think it'll just keep becoming more and more valuable -- I can put most of my team's code in Gemini 2.0 now.

Re: GitHub Copilot: The Agent Awakens

#253

Post by rstuart4133 »

throw83288 wrote: post #115
toprerules wrote: post #98

Earlier quoted context omitted.

This must be your first hype cycle then. Most of us who are senior+ have been through these cycles before. There's always a 10% gap that makes it impossible to fully close the gap between needing a programmer and a machine doing the work. Nothing about the current evolution of LLMs suggests that they are close to solving this. The current messaging is basically, look how far we got this time, we will for sure reach A…

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.

> So Work=0.1^Ct where C is the development pace.

Did you see the bit where he said "Most of us who are senior+ have been through these cycles before". They rolled out similar equations in previous hype cycles.

The LLM's were released about 3 years ago now. Over the weekend I made the mistake on taking their word on "does GitHub allow administrator to delete/hide comments on PR's". They convincingly said "no". Others pointed out the answer is of "yes". That's pretty typical. As far as I can tell, while their answers are getting better and more detailed, what happens when they reach the limits of their knowledge hasn't changed. They hallucinate. Convincingly.

That interacts with writing software in an unfortunate way. You start off by asking questions, getting good answers, and writing lots of code. But then you reach their limits, and they hallucinate. A new engineer has no way to know that's what happened, and so goes round and round in circles, asking more and more questions, getting complete (but convincing) crap in response, and getting nowhere. An experienced engineer has enough background knowledge to be able to detect the hallucinations.

So far, this hasn't changed much in 3 years. Given the LLM's architecture, I can't see how it could change without some other breakthrough. Then they won't be called LLM's any more, as it will be a different design. I'm have no doubt it will happen, but until it does LLM's are a major threat software engineers.

Re: GitHub Copilot: The Agent Awakens

#254

Post by hirako2000 »

makerdiety wrote: post #235
hirako2000 wrote: post #39

Earlier quoted context omitted.

More time for the things I do? All AI tools I've used turned my daily into fighting the agent. While LLMs can save time on tedious repetitive tasks, they are atrocities in producing bug free code. Even if they reached 99.999% accuracy without, they wouldn't be worth it: If I wrote a function and it turns out buggy, I can, even months later, investigate and find the culprit. If an LLM introduces a bug, I would rather…

If LLMs could produce innovative solutions, they wouldn't be large language models. They'd be valuable and indispensable software engineers to covet instead. Don't you agree that having a free artificial junior developer at your beck and call is better than not having freely and quickly produced code that can help point you into the direction your engineering needs to go in? As a senior developer, don't you also figh…

I wouldn't agree to call any of that a developer, adding junior to the term doesn't move the needle.

I wouldn't call a calculator a mini accountant. These things can operate much faster than an army of mathematicians but they remain tools. Of course l, tools humans can leverage. Productivity gains are phenomenal.

Perhaps my input to the topic wasn't clear. I use LLMs. I use LLMs in the context of software engineering. I don't treat them as my peers. I don't dream of a future where this tech can solve more than its often misunderstood scope.

We are letting ourselves be confused by those who do have an interest in, or can't do better than, up selling.

Engineers are already having to deal with very difficult to reconcile side effects. Maybe you aren't seeing it yet, or your comment would have at least recognized and touched on those.

Re: GitHub Copilot: The Agent Awakens

#255

Post by bluerooibos »

threatofrain wrote: post #31
aresant wrote: post #13

“Copilot puts the human at the center of the creative work that is software development. AI helps with the things you don’t want to do, so you have more time for the things you do.” … until we train our model on your usage data and totally replace you

If we actually could get to a world where programmers can be replaced, we'll also likely find that vast swathes of the population will be replaced. Then we'll need a totally new conversation on how society should look. That conversation is coming no matter what, because there will not be a global consensus to stop ML development, esp. on the war front.

I mean this is literally happening as we speak - the process has started and it's accelerating.

Governments need to be talking about this like yesterday, and very few are from what I'm seeing.

AI companies and others using AI are going to profit from this massively, at the expense of many more. We need a better tax system to redistribute these profits across society as a whole.

The issue is capitalism but AI exploding is going to exacerbate wealth inequality like nothing else.

Re: GitHub Copilot: The Agent Awakens

#256

Post by mywittyname »

scarface_74 wrote: post #220
mywittyname wrote: post #159

Earlier quoted context omitted.

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 enti…

> 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 I’m saying this ironically as a 50 year old (check my username) - “okay boomer”. That doesn’t work anymore. Internships are much harder to get than the…

Sucks to hear about the internships. I figured they'd still be relevant as I was mentoring people in an internship pipeline just 5 years ago, but a lot has changed since then. I do wonder how the effects graduation rates, as one of the reason we had so many interns at my previous job was because the local engineering school required an internship to graduate.

You're right though, shit is fucked. I didn't want to say that and have the person in our conversation thread get even more disheartened - that isn't helpful to them. But I agree with you and my experience job hunting just last year mirrors what you are saying. I've been thinking of what I'd do if I got laid off and well, sounds like it won't be a good time.

Re: GitHub Copilot: The Agent Awakens

#257

Post by makerdiety »

hirako2000 wrote: post #254
makerdiety wrote: post #235

Earlier quoted context omitted.

If LLMs could produce innovative solutions, they wouldn't be large language models. They'd be valuable and indispensable software engineers to covet instead. Don't you agree that having a free artificial junior developer at your beck and call is better than not having freely and quickly produced code that can help point you into the direction your engineering needs to go in? As a senior developer, don't you also figh…

I wouldn't agree to call any of that a developer, adding junior to the term doesn't move the needle. I wouldn't call a calculator a mini accountant. These things can operate much faster than an army of mathematicians but they remain tools. Of course l, tools humans can leverage. Productivity gains are phenomenal. Perhaps my input to the topic wasn't clear. I use LLMs. I use LLMs in the context of software engineering…

A bad developer is still a developer. Even if that developer is largely wrong, the majority of the employed developer's operating time consisting of unproductive efforts that will always need to be remedied by expert problem solving and engineering. But the LLM is such a naughty developer that is free (insofar as the pennies worth of electricity and microprocessor metals for running a local LLM is virtually no cost). Not only is it free, it is also able to give you a huge volume of labor. So, an LLM can give you a volume of free labor. And within the probability distribution of that large volume of free labor, there is the chance that bad developer will give you something valuable that can be productive and make up for all the losses you endured dealing with the eager assistant LLM developer. The bottom line is that being a skilled developer will require the employment of artificial intelligence's presently unwieldy enthusiasm and capability. As a sort of necessary evil that has on the opposite side of the bad side, the good side, unexpected insights, massive productivity, and unprecedented development. LLMs are probably the only way to perform the work of a hundred men all by yourself.

Unless what you're doing doesn't demand risk taking, perseverance, and a visionary's personality? In which case, we should call a spade a spade and, therefore, recognize that most (if not all) so called senior software developers are nothing more than state welfare recipients who are fungible to companies and economics that can get rid of the drag on their progress if they really wanted to. If you're not learning how to struggle with LLMs, you're probably not improving and growing as a software engineer. You'll then be limited to tentatively useful areas of the Internet. Like working for a FAANG, Tesla, or SpaceX or some other mundane shit.

Re: GitHub Copilot: The Agent Awakens

#258

Post by GrzegorzWidla »

throw83288 wrote: post #214
ddingus wrote: post #187

Earlier quoted context omitted.

IMHO what you should be doing is building stuff to show off. More great ideas will flow out of that activity. As for missed the boat, how do you mean? We remain in early days! Finally, try to avoid making your own reality. You write as if you know the future, and none of us do! And even when we are right, how we respond to that future really matters! You could sulk in gloom , or! You could be building things and or s…

I want to build but I don't know what. The ideas don't appear. This is what I've been trying to express.

My buddy recently had asked me whether he should pivot into software dev. I told him: if you have a problem to solve through programming, learn to code and do it; if you don’t, don’t. Programmers that will survive LLM revolution naturally find problems to solve. If you aren’t such a person it might not be a direction for you.

Re: GitHub Copilot: The Agent Awakens

#259

Post by elena2223 »

My husband has been frequently deleting all messages for the last couple of days from his phone and he didn’t know i was peeping at him, then i asked him why he was deleting all messages from his phone but he claimed that his phone memory was full and needed more space. Immediately I went in search of a hacker who can get me deleted information and contents from my husband’s phone and luckily for me i came across this reputable ethical hacker ETHICALTECHHACK, this hacker got the job done for me and provided me with results and i saw that my husband has been lying to me. He was simply deleting all pictures, call logs, chats and text messages,Whatsapp messages between him and his secret lover so i wont get to see what he has been doing at my back. Thank God for reputable hackers who are ready to help. I must say am really impressed with the services i got from The hacker Detective and am here to say a very big thank you: contact him on (ethicaltechhack @ gm ail com ).

Re: GitHub Copilot: The Agent Awakens

#260

Post by elena2223 »

If you suspect that someone is tracking your digital footprints, do not hesitate to reach out to (ETHICALTECHHACK) and kindly contact their mail for more consultation (ethicaltechhack @ . ), Their expertise will empower you to reclaim your privacy and security in the digital world.
Post reply on HN