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

What will LLM-powered software look like in the medium-term future?

vishnumenon.com

Post reply on HN
Print view View original

121–130 of 219 posts

Re: What will LLM-powered software look like in the medium-term future?

#121

Post by hirundo »

croo wrote: post #83

I'll tell you my vision which is kinda long term - like 20-30 year from now on. I think the future is that everyone will have their own personalized AI assistant on their phone. Internet as it is will be mostly useless because only robots will be able to wade through the generated shit ocean and the next generation will see it as the current see the TV - unimportant old boring low-entropy data which is not entertaini…

> the next generation will see it as the current see the TV - unimportant old boring low-entropy data which is not entertaining anymore.

Don't you mean high-entropy data? High entropy data would be less orderly, more compressible, and have a lower signal to noise ratio ... like TV shows compared to a textbook.

Re: What will LLM-powered software look like in the medium-term future?

#122

Post by amelius »

tarasglek wrote: post #26

@vishnumenon, thanks for writing this up. I might do a followup blog on this, for now here is a comment :) This article is close to my heart as I've been working on craftcraft.org with similar perspective. 1. Chat UX Consolidation: I agree that having crappy chat UIs everywhere is very suboptimal. Perhaps having a complete UX as a component is another solution here. We took many months to get http://chatcraft.org fro…

Your back button does not work!

Re: What will LLM-powered software look like in the medium-term future?

#123

Post by kyleyeats »

timacles wrote: post #103
gumballindie wrote: post #50

Earlier quoted context omitted.

To this day i am still wondering what kind of code people write that chatgpt can possibly help with. All my attempts lead to garbage and i would spend more time fixing the output of the chat bot than writing the actual code. It does help with some documentation. But even that has glitches.

It’s good at a beginner, early intermediate level when you need help with syntax and structuring basic things. It’s an excellent helper tool at that stage. But it’s obvious outside of jr dev work and hobby projects there’s no way it could possibly grasp enough context to be useful.

Stage? A lot of developers don't realize that they're all the same personality type which is good at particular things. LLMs give everyone else this advantage. You just don't realize it yet because you were never aware of the advantage in the first place.

Re: What will LLM-powered software look like in the medium-term future?

#125

Post by bumbledraven »

n4r9 wrote: post #74
corethree wrote: post #61

Earlier quoted context omitted.

Mathematically oriented software engineers have the most to benefit off of software assistance due to algebraic designs. As one myself LLMs don't feel like giving up control it feels like collaboration. You probably don't like collaboration.

Could you expand on the comment about "algebraic designs"? When I interact with an LLM it feels like I'm speaking to someone who lacks inherent conceptual understanding, but is doing their utmost best to bullshit me. This is problematic when it comes to algorithmic thinking. I sometimes need to solve problems that involve tweaking existing algorithms in somewhat novel ways. For example "k-medoid clustering but with v…

An LLM is going to be most helpful for topics that came up a lot during training. What you're discussing doesn't sound like it falls into that category.

Re: What will LLM-powered software look like in the medium-term future?

#126

Post by amelius »

Traubenfuchs wrote: post #5

I feel like us not being in that future right now means we won‘t get there so fast. What‘s missing to get all of this now? What recolutionary research, product development that hasn‘t happened yet will happen in the coming year? To me it looks like LLM tech is stagnating, after the hype peak we are close to the trough of disillusionment.

The problem with LLMs as I see it is that they make logic errors all the time, and somehow LLMs themselves are not smart enough to reason about their own reasoning.

Re: What will LLM-powered software look like in the medium-term future?

#127

Post by inimino »

hirundo wrote: post #121
croo wrote: post #83

I'll tell you my vision which is kinda long term - like 20-30 year from now on. I think the future is that everyone will have their own personalized AI assistant on their phone. Internet as it is will be mostly useless because only robots will be able to wade through the generated shit ocean and the next generation will see it as the current see the TV - unimportant old boring low-entropy data which is not entertaini…

> the next generation will see it as the current see the TV - unimportant old boring low-entropy data which is not entertaining anymore. Don't you mean high-entropy data? High entropy data would be less orderly, more compressible, and have a lower signal to noise ratio ... like TV shows compared to a textbook.

Low entropy data is what's more compressible. High entropy means unpredictable, which could mean high noise (like TV static which is incompressible) or high signal as GP intended.

Re: What will LLM-powered software look like in the medium-term future?

#128

Post by bostonsre »

gumballindie wrote: post #50
ryanjshaw wrote: post #38

> I don’t believe that natural language is an adequate medium for conveying instructions with the precision required for many applications. Not clear to me if the author actually uses LLMs to do meaningful work, or is speculating about how they might be used. I've written about 2500 lines of F# for the first time in the past 1.5 weeks using ChatGPT-4 to guide me. It has been an constant back and forth, iterative proc…

To this day i am still wondering what kind of code people write that chatgpt can possibly help with. All my attempts lead to garbage and i would spend more time fixing the output of the chat bot than writing the actual code. It does help with some documentation. But even that has glitches.

If you are trying to do something with an api that you have no experience with it will get you up and running quickly. e.g. How do I get all kubernetes configmaps in a given namespace older than n days in go? It gives you the bones about how you create and configure a client and query kubernetes to get the information that you are looking for. It's much quicker than googling and parsing a tutorial.

Re: What will LLM-powered software look like in the medium-term future?

#129

Post by InitialLastName »

croo wrote: post #111
wbm1 wrote: post #100

Earlier quoted context omitted.

An LLM/AI companion based on your ledger, that grows and evolves with you, acting as a sort of Socratic daimon, a psychologic twin, assistant, advisor, and sparring partner. Like a journal that talks back and thinks with you. It'd need to be only personally accessible and safe/private. Biometric access and local running could solve this.

Exactly! Most will have a name given by its owner, a pet of sort but much more in function. You will need to reach a certain age to get it, the beginning of adulthood. People will mourn them and there will be real world AI cementeries. Diffie Whitfield envisioned an internet highway where every computer is connected to every other in 1974 and then went on to find out how to do that communication in secure channels.[1…

> You will need to reach a certain age to get it, the beginning of adulthood.

Not a chance will whatever capitalist figures out how to do this allow a measly cultural restriction keep them from pushing that age deep into childhood.

Re: What will LLM-powered software look like in the medium-term future?

#130

Post by bumbledraven »

deelly wrote: post #58
_8j50 wrote: post #51

Earlier quoted context omitted.

I feel like such a jerk for not wanting to use chatgpt for all that. It's not just mild paranoia about feeding it input I prefer be kept private but I just don't enjoy having someone else do half the thinking for me I guess. I mean, I don't like intellisense either (but simple autocomplete is fine). Perhaps it is because I only code to help with my job, I don't get paid to have a lot of good quality code output.

I know exactly why I don't want to use ChatGPT. I love to write code, I love to modify existing code too. I do not love to read and then fix code after someone all the time. With ChatGPT I have to read then understand then fix code after ChatGPT every time. Also, I do not love to fix code that often contains hallucination.

First, are you sure using GPT-4?

Second, have you tried pasting any syntax errors you get back into the chat window? Usually, GPT will try to fix them.

Third, you can have GPT write a function for you and then write a different version of the function using a different algorithm along with a test (e.g. a fuzz test) to check whether two functions produce the same output given the same input. This makes it less likely that an error will slip through because both algorithms would have to be produce the same incorrect output for the same input.

Post reply on HN