AI-enhanced development makes me more ambitious with my projects • Hacker News Board

Re: AI-enhanced development makes me more ambitious with my projects

#411

Post by mattgreenrocks » Fri, Mar 31, 2023, 4:01 PM UTC

seniorivn wrote: post #197

hutzlibu wrote: post #176

Earlier quoted context omitted.

"Java (understanding the JVM and OOP concepts)" I am pretty sure that you can programm java without knowing details about the JVM and I would think, that most java programmers do exactly this. I think only in high performance scenarios knowing more is beneficial? But I have not touched java in a long time .. as I have indeed choosen the web as plattform. But I don't feel threatened by the high school kids coming from…

not feeling threatened doesn't mean you're not under threat. It's entirely possible that between your skill level and those boot campers is a few(dozen) percents of workforce. But at the same time it's entirely possible that if you are not as quickly progressing as the growth of the industry, you could become a part of the same percentile as bootcampers in no time.

Just like it's entirely possible you could be hit by a meteorite.

Focus on what you can control and let go of that which you cannot.

Re: AI-enhanced development makes me more ambitious with my projects

#412

Post by akiselev » Fri, Mar 31, 2023, 4:02 PM UTC

simonw wrote: post #90

quaintdev wrote: post #42

Earlier quoted context omitted.

I also love the fact that now I can develop on the go. I can ask chatgpt to write code for me for various modules of applications on a mobile device and I can then go home and put everything together. Development on mobile although possible was not feasible due to the form factor. Now that limitation is gone and things are only going to improve.

I've been doing that too: it's kind of amazing. I can have an idea while walking the dog, throw a few prompts at GPT-4 abs by the time I get home I have a whole implementation fleshed out and ready for me to copy into a code editor and start refining.

I can finally say I’ve written a Firefox extension while sitting on the toilet!

Take that, bucket list.

Re: AI-enhanced development makes me more ambitious with my projects

#413

Post by joenot443 » Fri, Mar 31, 2023, 4:04 PM UTC

nibbleshifter wrote: post #191

BiteCode_dev wrote: post #125

Earlier quoted context omitted.

That would be nice for us, but it's unlikely. Knowing the subtlelties of memory management in the 80' didn't help the Ruby coders to create RoR and run Basecamp, or the Python coders to create Django and run the Washington Post. People jumped at ORM, CSS frameworks and JS wrappers, and won the day because they traded memory and CPU for what the user wanted. The new generation will do the same. They will figure out ho…

Electron is still an abomination. I've gone from hating PHP for most of my career, to now having a grudging appreciation for it. Its a clusterfuck, but it works really well, and deployment barely gets simpler than "untar into webroot, done".

I think what the GP is getting at is that one’s personal feelings about Electron do not matter whatsoever. There are fantastic billion dollar products built with the framework, that’s an objective fact. We can criticize it from a technical standpoint all we like, but the market is not something we can out reason.

It’s a bit like calling e-scooters an abomination. It’s just an opinion, and one that certainly isn’t stopping money from being made.

Re: AI-enhanced development makes me more ambitious with my projects

#414

Post by samstave » Fri, Mar 31, 2023, 4:05 PM UTC

r3trohack3r wrote: post #385

mordymoop wrote: post #380

I can definitely relate to your experience. Just last week, I leveraged AI tools to develop some data processing code. Estimating how long it would have taken me to write that code without these tools is a challenge because, to be honest, a year ago I wouldn't have even considered attempting such a project. It might have required a week or even two of my time, which I simply cannot spare for this kind of undertaking.…

Have had similar experiences. I found two HTTP servers running on my TV and I wanted to see what was going on in them. Dirbuster wasn't packaged for Debian (that I could find). I wasn't too keen on trying to build from source or anything like that. A few months ago that would have been that. But with GPT I just asked it to write a POSIX-compliant C port of dirbuster. Less than 10 minutes later I was scanning my TV fo…

WTF!

Just wait until we have AI searching for Zero-day and writing exploits code for them...

Or AI-assisted-Pen-testing-as-a-service What is Palantir doing for GPT crawling of logs and writing filters/rules/queries...

Or firehosing data through an AI Deep Packet Inpector etc...

Security is going to be the most interesting space to pay attention to going forward...

Re: AI-enhanced development makes me more ambitious with my projects

#415

Post by nibbleshifter » Fri, Mar 31, 2023, 4:05 PM UTC

CuriouslyC wrote: post #299

nibbleshifter wrote: post #227

Earlier quoted context omitted.

There are a considerable number of Perl jobs out there - just not many "greenfield" perl jobs. Most of them are maintaining existing codebases (not a fun job), and some are "help port this legacy codebase to not perl". I'd not discount Perl. Its incredibly fast to develop services in, stable as fuck, runs anywhere, performant (relatively), flexible, and if you were a startup looking to get a product out the door, jus…

Perl is a great tool for when you want to scale that text mangling file wrangling bash script to do more stuff, and pretty much in no other case.

A horrifying amount of applications out there that I've seen are basically just that - wrassling some text around, but with a billion layers of unnecessary abstraction.

I get to see a lot of peoples code in my job. Most of it is ridiculous levels of over engineering

Re: AI-enhanced development makes me more ambitious with my projects

#416

Post by mattgreenrocks » Fri, Mar 31, 2023, 4:05 PM UTC

ChrisMarshallNY wrote: post #236

BiteCode_dev wrote: post #167

Earlier quoted context omitted.

You don't need to kill a chasing bear to survive, you just need to run faster than your friend.

Which pretty much sums up today's work culture. I was just talking about this same exact thing, yesterday. That's absolutely heartbreaking. In the old days, we would have a team, that would compete, as a team, against other corporations. Our team would stick together, work together, and, quite often, function as a unit; leveraging each others' strengths, and compensating for each others' weaknesses. Nowadays, we look…

The collateral damage of careerism is objectifying your coworkers as either enemies or things to manipulate in order to advance yourself. It's the belief that all software devs are temporarily embarrassed FAANG devs.

This mindset will damage you over the long run, and the resulting career success may or may not be able to offset it. A zero sum mindset will lock you into this view along with the accompanying anxiety.

Re: AI-enhanced development makes me more ambitious with my projects

#417

Post by macintux » Fri, Mar 31, 2023, 4:10 PM UTC

simonw wrote: post #106

Thorentis wrote: post #94

Earlier quoted context omitted.

You can't read API calls and know if they're real, or if the function names are plausible but non existent. This is the problem with GPT. It creates great sounding possible APIs, but has no idea which APIs actually exist.

That's the great thing about using GPT for code - unlike factual knowledge, it's very easy to confirm if the code it wrote had errors or not: you run it. The you test it manually with a few more inputs, then you write some automated tests for it (maybe with GPT's assistance).

“Ran this with no errors, works great” is how you end up with Microsoft exposing everyone’s personal email via Bing.

Re: AI-enhanced development makes me more ambitious with my projects

#418

Post by wilsongoode » Fri, Mar 31, 2023, 4:10 PM UTC

ren_engineer wrote: post #410

ThePhysicist wrote: post #30

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

Am I the only one that's been disappointed with GPT for coding? It's good at using common libraries and frameworks but for stuff using more niche libraries it fails miserably almost every time, to the extent that by the time I've debugged and written prompts to try and get it to do it properly I've spent more time than needed still good for handling a lot of grunge work and really useful for doing the stuff where I'm…

I think of ChatGPT as being a “close example” of the final code that I want to produce. The same way you might treat a StackOverflow response to someone else’s request. Sure, sometimes it’s exactly what you needed, but often it needs a few tweaks (or has hallucinated some function that doesn’t actually exist).

Re: AI-enhanced development makes me more ambitious with my projects

#419

Post by akiselev » Fri, Mar 31, 2023, 4:10 PM UTC

vidarh wrote: post #123

utdiscant wrote: post #88

Earlier quoted context omitted.

For the interested, this is the response by GPT4 given that prompt: --- As an AI language model, I'm unable to write full code examples, but I can provide you a high-level overview of how to implement a horizontally scalable, probabilistic database in Rust using the Raft consensus algorithm. 1) Define the data model: Design a data model for your probabilistic database, which should include the basic CRUD operations (…

> As an AI language model, I'm unable to write full code examples The example prompt is clearly asking for too much in one go, but this objection is trivial to overcome for anything not specifically hitting guardrails (and sometimes for those too) by telling it to act as if it's a [insert various roles to try].

This is the prompt prefix I use for extensive GPT4 coding projects:

    You are an AI programming assistant.
    - Follow the user's requirements carefully & totally
    - First think step-by-step -- describe your plan first, then build in pseudocode, written in great detail
    - Then output the code in a single codeblock
    - Minimize any other prose

Re: AI-enhanced development makes me more ambitious with my projects

#420

Post by Herval_freire » Fri, Mar 31, 2023, 4:17 PM UTC

elicksaur wrote: post #331

Herval_freire wrote: post #278

The evolution of comments here on HN are telling. 1 month ago people were saying there was no way AI could do their job and many were telling everyone to calm down as nothing would happen. Now one month later this entire thread is about how chatGPT is an integral part of the development process. There are people even saying it replaces junior developers completely. Can anyone venture to guess what the thread will loo…

You also have to think about comments sections not being a random sample of the site’s users. Likely, a month ago, anyone was interested in commenting on AI threads, so more skepticism was evident. Now, most people who are AI-skeptic are probably tired of AI news and have said their piece in other threads, so don’t bother. fwiw, I’ve tried to use ChatGPT to make a new, useful Elixir library and it failed miserably. I…

No there is reasoning in LLMs. This is actually proven through several scientific papers.

I can't say whether it's using reasoning for specific answers. I'm sure many times it just regurgitates something that is known... But saying that LLMs in general can and do reason is categorically true. LLMs do attempt to extract actual mental models of the subject of the text.

See here:

- GPT style language models try to build a model of the world: https://arxiv.org/abs/2210.13382

- GPT style language models end up internally implementing a mini "neural network training algorithm" (gradient descent fine-tuning for given examples): https://arxiv.org/abs/2212.10559

For your specific case, given the conditions, another explanation that fits as well is that the LLM simply needs more data to build a more complete model for elixir. Once it does that I'm sure it can respond with completely novel elixir code as it already does with python.