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

GitHub cuts AI deals with Google, Anthropic

bloomberg.com

Post reply on HN
Print view View original

551–560 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#551

Post by Vegenoid »

zkry wrote: post #522
ianbutler wrote: post #311

Earlier quoted context omitted.

I'm actually very curious why AI use is such a bi-modal experience. I've used AI to move multi thousand line codebases between languages. I've created new apps from scratch with it. My theory is the willingness to baby sit and the modality. I'm perfectly fine telling the tool I use its errors and working side by side with it like it was another person. At the end of the day it can belt out lines of code faster than I…

I'm curious coming from the other end. I guess I can totally understand certain use cases where I'm generating fairly simple, self contained code in a language I'm unfamiliar with being good. But surely you must have experienced something where you're literally fighting with the model, where it continuously repeats its mistakes, and fixing a mistake in one place, breaks something else, and you can't seem to escape th…

This is my experience. I’d love to see some full streams of people building whole useful apps from scratch with an LLM, does anyone have any good examples?

Re: GitHub cuts AI deals with Google, Anthropic

#552

Post by anonzzzies »

nwienert wrote: post #487
afro88 wrote: post #477

Earlier quoted context omitted.

> But the idea of letting an LLM write/move large swaths of code seems so incredibly irresponsible. I think this is where the bimodality comes from. When someone says "I used AI to refactor 3000 loc" some take it to mean they used AI in small steps as an accellerator, and others take it to mean a direct copy/paste, fix compile errors and move on. Treat AI like a mid level engineer that you are pair programming with,…

It’s really far from mid level. It’s a weird mix of expert at things it trained on, and complete misleading idiot at anything outside. For a bash script or the first steps of something simple it’s great. For anything complex at all it’s worse than nothing.

Works well for us nonetheless, also on more complex things. It's not worse than most (including seniors) humans I worked with in the past 40 years, but it is faster and cheaper. On HN it is sometimes forgotten that by far most programmers do not like it; they need money. If you see what comes out of them, you have to puke; yet it's running billion$ businesses and works surprisingly well considering the bad code quality.

Re: GitHub cuts AI deals with Google, Anthropic

#553

Post by hitradostava »

geysersam wrote: post #365
0xFACEFEED wrote: post #329

Earlier quoted context omitted.

As a programmer of over 20 years - this is terrifying. I'm willing to accept that I just have "get off my lawn" syndrome or something. But the idea of letting an LLM write/move large swaths of code seems so incredibly irresponsible. Whenever I sit down to write some code, be it a large implementation or a small function, I think about what other people (or future versions of myself) will struggle with when interactin…

I'll take a stab at changing your mind. AIs are not able to write Redis. That's not their job. AIs should not write complex high performance code that millions of users rely on. If the code does something valuable for a large number of people you can afford humans to write it. AIs should write low value code that just repeats what's been done before but with some variations. Generic parts of CRUD apps, some fraction…

In a couple of years time I don't see why AI based tooling couldn't write Redis? Would you get a complete Redis produced with a single prompt? Of course not. but if extreme speed is what you want to optimize for, then the tooling needs to be given the right feedback loop to optimize for that.

I think the question to ask is what do I do as a software engineer that couldn't be done by an AI based tool in a few years time? The answer is scary, but exciting.

Re: GitHub cuts AI deals with Google, Anthropic

#554

Post by DeathArrow »

hackable_sand wrote: post #409
bob1029 wrote: post #246

Earlier quoted context omitted.

It's the subtle errors that are really difficult to navigate. I got burned for about 40 hours on a conditional being backward in the middle of an otherwise flawless method. The apparent speed up is mostly a deception. It definitely helps with rough outlines and approaches. But, the faster you go, the less you will notice the fine details, and the more assumptions you will accumulate before realizing the fundamental e…

I would love to find out where programmers are learning this idea: that writing code fast is ideal. If it takes 30 years to write one loc, it takes 30 years. Ideally, it takes 30 years to write zero lines of code.

>where programmers are learning this idea:

>that writing code fast is ideal.

At places that pay them.

Re: GitHub cuts AI deals with Google, Anthropic

#555

Post by globular-toast »

pyeri wrote: post #431

Call me eccentric but the only true or utilitarian use case I've found for AI so far is chatgpt. Rest all appear to be shiny toys just trying to bask in the AI glory but none solve any real human problem?

Even ChatGPT is rubbish. Try to figure out something you couldn't find in a book and it will end up contradicting itself before long. If it gets it right that just means you could have found it in a book. I've been immersed in the internet my whole life and I still think books are the best source of knowledge. Curation and editing are what we need more of.

Re: GitHub cuts AI deals with Google, Anthropic

#556

Post by hitradostava »

RheingoldRiver wrote: post #546
hitradostava wrote: post #545

Earlier quoted context omitted.

I agree with you and its confusing to me. I do think there is a lot of emotion at play here - rather than cold rationality. Using LLM based tools effectively requires a change in workflow that a lot of people aren't ready to try. Everyone can share their anecdote of how an LLM has produced stupid or buggy code, but there is way too much focus on what we are now, rather than the direction of travel. I think existing m…

> Using LLM based tools effectively requires a change in workflow that a lot of people aren't ready to try This is a REALLY good summary of it I think. If you lose your patience with people, you'll lose your patience with AI tooling, because AI interaction is fundamentally so similar to interacting with other people

Exactly, and LLM based tools can be very frustrating right now - but if you view the tooling as a very fast junior developer with very broad but shallow knowledge then you can develop a workflow which for many (but not all) tasks is much much faster writing code by hand.

Re: GitHub cuts AI deals with Google, Anthropic

#557

Post by uberswe »

DeathArrow wrote: post #549

For all those believers in the power of AI who tested it in modifying their front-ends and writing a Python script, I have a test: ask AI to write an operating system kernel or a database. Of course, something simple. I never seen AI being used in writing system software. Perhaps there is a reason behind it?

From experience no AI solution is consistently making fault free code of any kind when you need more than a snippet.

Personally I have been making Velocity Proxy plugins for Minecraft where ChatGPT generates the bulk of the plugin and I fix all the incorrect imports, this is Java. My latest project was a whitelist plugin that uses Discord roles to allow/deny players to join.

Re: GitHub cuts AI deals with Google, Anthropic

#558

Post by Kiro »

CephalopodMD wrote: post #404

I usually feel like i can confidently express a change I want in code faster and better than I can explain what I want an AI to do in English. Like if I have a good prompt, these tools work okay, but getting that prompt almost as hard as just writing the code itself often. Do others feel the same struggle?

You learn how to effectively prompt it in a way where the AI can fill in the blanks. Sometimes the prompt is just a couple of words because I know that the AI will interpolate the rest by the context (getting the context right is crucial). However, even when I need to be verbose and have to spend a few minutes on a prompt it gives me code that would have taken half a day to write manually. You also need to learn how and when to split work into chunks. It's much less intuitive than one would think and is completely different than how you would split it for a human. You get to "know" the AI and what it needs in order to succeed with a task.

LLMs have other problems though. The biggest problem for me is that it feels like I lose control of the codebase. I don't have the same mental mapping of the code.

Re: GitHub cuts AI deals with Google, Anthropic

#559

Post by DeathArrow »

tensor wrote: post #306
bob1029 wrote: post #246

Earlier quoted context omitted.

It's the subtle errors that are really difficult to navigate. I got burned for about 40 hours on a conditional being backward in the middle of an otherwise flawless method. The apparent speed up is mostly a deception. It definitely helps with rough outlines and approaches. But, the faster you go, the less you will notice the fine details, and the more assumptions you will accumulate before realizing the fundamental e…

Why aren't you writing unit tests just because AI wrote the function? Unit tests should be written regardless of the skill of the developer. Ironically, unit tests are also one area where AI really does help move faster. High level design, rough outlines and approaches, is the worst place to use AI. The other place AI is pretty good is surfacing api call or function calls you might not know about if you're new to the…

I am kind of starting to doubt about the utility of unit tests. From a theoretical perspective I see the point in writing unit tests. But in practice I rarely seen them being useful. Guy A writes poor logic and sets in stone that poor logic by writing an unit test. Manual testing discovers a bug so guy B has to modify that poor logic and the unit test.

I'd rather see the need for integration tests and end to end tests. I want to test business logic not assert that 2 + 2 = 4.

Re: GitHub cuts AI deals with Google, Anthropic

#560

Post by DeathArrow »

tensor wrote: post #382
chairhairair wrote: post #318

Earlier quoted context omitted.

I have completely the opposite perspective. Unit tests actually need to be correct, down to individual characters. Same goes with API calls. The API needs to actually exist. Contrast that with "high level design, rough outlines". Those can be quite vague and hand-wavy. That's where these fuzzy LLMs shine. That said, these LLM-based systems are great at writing "change detection" unit tests that offer ~zero value (or…

The fact that you think "change detection" tests offer zero value speaks volumes. Those may well be the most important use of unit tests. Getting the function correct in the first place isn't that hard for a senior developer, which is often why it's tempting to skip unit tests. But then you go refactor something and oops you broke it without realizing it, some boring obvious edge case, or the like. These tests are al…

>The fact that you think "change detection" tests offer zero value speaks volumes.

But code should change. What shouldn't change, if business rules don't change, is APIs and contracts. And for that we have integration tests and end to end tests.

Post reply on HN