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

271–280 of 742 posts

Re: GitHub cuts AI deals with Google, Anthropic

#271

Post by tanseydavid »

bob1029 wrote: post #246
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

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…

>> The apparent speed up is mostly a deception.

When I am able ask a very simple question of an LLM which then prevents me having to context-switch to answer the same simple question myself; this is a big time saver for me but hard-to-quantify.

Anything that reduces my cognitive load when the pressure is on is a blessing on some level.

Re: GitHub cuts AI deals with Google, Anthropic

#273

Post by Nevermark »

enneff wrote: post #266
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…

That’s the thing, isn’t it? The craft of programming in the small is one of being intimate with the details, thinking things through conscientiously. LLMs don’t do that.

Perhaps it should be prompted to then?

Ask it to review its own code for any problems?

Also identify typical and corner cases and generate tests?

Question marks here because I have not used the tool.

The size & depth of each accepted code step is still up to the developer slash prompter

Re: GitHub cuts AI deals with Google, Anthropic

#275

Post by jascha_eng »

realce wrote: post #260
SparkyMcUnicorn wrote: post #237

Earlier quoted context omitted.

I haven't used Cursor, but I use Aider with Sonnet 3.5 and also use Copilot for "autocomplete". I'd highly recommend reading through Aider's docs[0], because I think it's relevant for any AI tool you use. A lot of people harp on prompting, and while a good prompt is important I often see developers making other mistakes like not providing context that's good, correct, or even too much[1]. When I find models are going…

Totally agree that heavy commenting is the best convention for helping the assistant help you best. I try to comment in a way that makes a file or function into a "story" or kind of a single narrative.

That's super interesting, I've been removing a lot of the redundant comments from the AI results. But adding new more explanatory ones that make it easier for both AI and humans to understand the code base makes a lot of sense in my head.

I was big on writing code to be easy to read for humans, but it being easy to read for AI hasn't been a large concern of mine.

Re: GitHub cuts AI deals with Google, Anthropic

#276

Post by kortilla »

MuffinFlavored wrote: post #224
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

> in practice I’m not noticing a productivity boost. How can this be possible if you literally admit its tab completion is mindblowing? Isn't really good tab completion good enough for at least a 5% producitvity boost? 10%? 20%? Select line of code, prompt it to refactor, verify they are good, accept the changes

If someone can eat 20 golf balls that’s impressive but it doesn’t improve my golf game

Re: GitHub cuts AI deals with Google, Anthropic

#277

Post by timeon »

ianeigorndua wrote: post #86
guerrilla wrote: post #73

Earlier quoted context omitted.

That was the point. They are laundering IP. It's the long way around the GPL, allowing then to steal.

How many OSS repositories do I personally have to read through for my own code to be considered stolen property? That line of thought would get thrown out of court faster than an AI would generate it.

This seems bit nihilistic. You can't be automated. You can't process repos at scale.

Re: GitHub cuts AI deals with Google, Anthropic

#278

Post by bradford »

MuffinFlavored wrote: post #224
thih9 wrote: post #221

I use cursor and its tab completion; while what it can do is mind blowing, in practice I’m not noticing a productivity boost. I find that ai can help significantly with doing plumbing, but it has no problems with connecting the pipes wrong. I need to double and triple check the updated code - or fix the resulting errors when I don’t do that. So: boilerplate and outer app layers, yes; architecture and core libraries,…

> in practice I’m not noticing a productivity boost. How can this be possible if you literally admit its tab completion is mindblowing? Isn't really good tab completion good enough for at least a 5% producitvity boost? 10%? 20%? Select line of code, prompt it to refactor, verify they are good, accept the changes

> How can this be possible if you literally admit its tab completion is mindblowing?

I might suggest that coding doesn't take as much of our time as we might think it does.

Hypothetically:

Suppose coding takes 20% of your total clock time. If you improve your coding efficiency by 10%, you've only improved your total job efficiency by 2%. This is great, but probably not the mind-blowing gain that's hyped by the AI boom.

(I used 20% as a sample here, but it's not far away from my anecdotal experience, where so much of my time is spent in spec gathering, communication, meeting security/compliance standards, etc).

Re: GitHub cuts AI deals with Google, Anthropic

#279

Post by oogetyboogety »

tanseydavid wrote: post #271
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…

>> The apparent speed up is mostly a deception. When I am able ask a very simple question of an LLM which then prevents me having to context-switch to answer the same simple question myself; this is a big time saver for me but hard-to-quantify. Anything that reduces my cognitive load when the pressure is on is a blessing on some level.

This might be the measurable "some" non deceptive time saving, whereas most of it is still deceptive in terms of time saved

Re: GitHub cuts AI deals with Google, Anthropic

#280

Post by dspillett »

outworlder wrote: post #240
MangoCoffee wrote: post #229

Earlier quoted context omitted.

Time will tell. As a GitHub Copilot user, I still review the code. SpaceX's advancements are impressive, from rocket blow up to successfully catching the Starship booster. Who knows what AI will be capable of in 5-10 years? Perhaps it will revolutionize code assistance or even replace developers

> SpaceX's advancements are impressive, from rocket blow up to successfully catching the Starship booster. That felt like it was LLM generated since that doesn't have anything to do with the subject being discussed. Not only it's on a different industry but it's a completely different set of problems. We know what's involved in catching a rocket. It's a massive engineering challenge yes, but we all know it can be don…

> Artificial intelligence? We don't know enough about "intelligence".

The problem I have with this objection is that it, like many discussions, conflates LLMs (glorified predictive text) and other technologies currently being referred to as AI, with AGI.

Most of these technologies should still be called machine learning as they aren't really doing anything intelligent in the sense of general intelligence. As you say yourself: they don't know anything. And by inference, they aren't reasoning about anything.

Boilerplate code for common problems, and some not so common ones, which is what LLMs are getting pretty OK at and might in the coming years be very good at, is a definable problem that we understand quite well. And much as we like to think of ourselves as "computer scientists", the vast majority of what we do boils down to boilerplate code using common primitives, that are remarkably similar across many problem domains that might on first look appear to be quite different, because many of the same primitives and compound structures are used. The bits that require actual intelligence are often quite small (this is how I survive as a dev!), or are away from the development coalface (for instance: discovering and defining the problems before we can solve them, or describing the problem & solution such that someone or an "AI" can do the legwork).

> we need other big advancements in the field, which may or may not come.

I'm waiting for an LLM being guided to create a better LLM, and eventually down that chain a real AGI popping into existence, much like the infinite improbability drive being created by clever use of a late version finite improbability generator. This is (hopefully) many years (in fact I'm hoping for at least a couple of decades so I can be safely retired or nearly there!) from happening, but it feels like such things are just over the next deep valley of disillusionment.

Post reply on HN