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

Software 3.1? – AI Functions

blog.mikegchambers.com

Post reply on HN
Print view View original

31–40 of 61 posts

Re: Software 3.1? – AI Functions

#31

Post by ryancoleman »

re-thc wrote: post #11
leoedin wrote: post #9

I can't even imagine how many joules would be used per function call! As an experiment, it's kind of cool. I'm kind of at a loss to what useful software you'd build with it though. Surely once you've run the AI function once it would be much simpler to cache the resulting code than repeatedly re-generate it? Can anyone think of any uses for this?

> run the AI function once it would be much simpler to cache the resulting code than repeatedly re-generate it? Surely, you'll run a function that does an AI call to cache the resulting code.

The initial version on GitHub does not implement caching or memorization but it's possible and where the project will likely head. (FYI I'm on the Strands Agents team).

Re: Software 3.1? – AI Functions

#32

Post by renegade-otter »

This has big "let's do this because we can" energy.

What is the BENEFIT of all this?

Let's use Blockchain instead of a database - because we can.

Let's create a maze of microservices - because we can.

Let's make every function a lambda function - because we can.

Let's make AI write code, run it, verify it, fix it, then run it again - because we can.

Let's burn untold amounts of energy to do simple things - because we can.

Re: Software 3.1? – AI Functions

#33

Post by renegade-otter »

stackghost wrote: post #16

I'm normally pessimistic about LLMs but I'll be the contrarian here and suggest there's actually a potential use case for what TFA proposes and it's programmatic/procedural generation for large game worlds.

There is a use for everything. The problem is, people will try to use this to create CRUD apps for no goddamned reason.

Re: Software 3.1? – AI Functions

#34

Post by simsla »

leoedin wrote: post #9

I can't even imagine how many joules would be used per function call! As an experiment, it's kind of cool. I'm kind of at a loss to what useful software you'd build with it though. Surely once you've run the AI function once it would be much simpler to cache the resulting code than repeatedly re-generate it? Can anyone think of any uses for this?

I've used stuff like this for a hobby project where "effort to write it" vs "times I'm going to use it" is heavily skewed [0]. For production use cases, I can only see it being worth it for things that require using an ML model anyway, like "summarize this document".

[0] e.g. something like the below which I expect to use maybe a dozen times total.

Main routine: In folder X are a bunch of ROM files (iso, bin, etc) and a JSON file with game metadata for each. Look for missing entries, and call [subroutine] once per file (can be called in parallel). When done, summarise the results (successes/failures) based on the now updated metadata.

Subroutine: (...) update XYZ, use metacritic to find metadata, fall back to Google.

Re: Software 3.1? – AI Functions

#35

Post by marginalia_nu »

renegade-otter wrote: post #32

This has big "let's do this because we can" energy. What is the BENEFIT of all this? Let's use Blockchain instead of a database - because we can. Let's create a maze of microservices - because we can. Let's make every function a lambda function - because we can. Let's make AI write code, run it, verify it, fix it, then run it again - because we can. Let's burn untold amounts of energy to do simple things - because we…

Because we can? More like because I have equity in a company that sells this stuff.

Re: Software 3.1? – AI Functions

#37

Post by stackghost »

renegade-otter wrote: post #33
stackghost wrote: post #16

I'm normally pessimistic about LLMs but I'll be the contrarian here and suggest there's actually a potential use case for what TFA proposes and it's programmatic/procedural generation for large game worlds.

There is a use for everything. The problem is, people will try to use this to create CRUD apps for no goddamned reason.

>There is a use for everything.

Eventually, perhaps. I've yet to see a use case for blockchains that isn't merely a worse facsimile of something already existing.

But the electron was useless when it was discovered, so maybe one day

Re: Software 3.1? – AI Functions

#38

Post by gdulli »

renegade-otter wrote: post #32

This has big "let's do this because we can" energy. What is the BENEFIT of all this? Let's use Blockchain instead of a database - because we can. Let's create a maze of microservices - because we can. Let's make every function a lambda function - because we can. Let's make AI write code, run it, verify it, fix it, then run it again - because we can. Let's burn untold amounts of energy to do simple things - because we…

Discretion will be the better part of the tech industry, if we ever reach that maturity level.

Re: Software 3.1? – AI Functions

#39

Post by snowhale »

manofmanysmiles wrote: post #19

I'd like to see this with a proper local "instruction cache." It might even be fun that the first call generates python (or other langauge), and then subsequent calls go through it. This "otpimized" or "compiled" natural langauge is "LLMJitted" into python. With interesting tooling, you could then click on the implementation and see the generated cod, a bit like looking at the generated asssembly. Usually you'd just…

[dead]
Post reply on HN