jmsdnns

yep. the comments are for folks who have never tried to read cobol before, which is probably 99% of people looking at the project. this way they can understand a familiar idea expressed in a language that is probably wildly different from what theyre used to.

for example IT IS YELLING AT US THE WHOLE TIME

the code is similar to fixed format, but the location of the comments gives away that it is actually in free format.

* comments use *> at start of line, though I'm not sure i'll keep that

* indentation is flexible, but i prefer how fixed looks

* no column restrictions

yep, it calls the external c function. same with setsockopt, bind, and listen further down.

thank you!

i helped Chris Callison-Burch design a class at upenn, called interactive fiction, which is a similar context to what Simon suggested. the real magic is that it reframes hallucinations as creative story telling. the usecase is SUPER fun if you imagine the LLM as a dungeon master telling a story that gets expanded over time.

the framework he and I built kept track of the game state over time and allowed saving and loading games as json. we could then send the full json to an LLM as part of the prompts to get it to react. the most neat part, imo, was when we realized we could have the LLM generate text for parts of the story, then analyze what it said to detect any items, locations, or characters not jn the game state, and then have it create json representations of the hallucinated objects that could be inserted into the game states. that sealed the deal for using hallucinations as creative story telling inside the context of a game.

i assure you the D&D context is very fun! the class website might give you more ideas too https://interactive-fiction-class.org/

i wasnt officially part of upenn at the time, so my name isnt listed on the site, but we wrote a paper about some of the things we did, such as this one, and you'll see me listed there https://www.cis.upenn.edu/~ccb/publications/dagger.pdf

hallucinations is when we dont like it, creativity is when we do

please check my other comment. it's not a wild rewriting, just needed clarification.

he was vocal about his opposition to intrusive ads in particular. he'd say "You’re either the customer or you’re the product." he believed users paid a premium for apple products and that they should not be subjected to compromises with advertising.

iAd was something that happened right at the end of his life because devs were putting ads in apple apps anyway and he wanted to control how that was done.

this is meant to add context to what bluedevilzn said, btw. it is not a refutation.

Jobs hated ads. You're right that he never wouldve done what Apple is doing now.

Cook needs to stop listening to investors, like Warren Buffett, because he's letting them wreck Apple's integrity for the sake of making a buck. Apple just isnt user focused like they used to be and it's crappy.

depending on what you're using the synthetic data for, it is sometimes called distillation. here is a robust example from some upenn students: https://datadreamer.dev/

Spec updates every three months are really tough, especially when not versioned, thoroughly documented, or archived properly.

Couldnt AI help with that..?

There is another angle to this too.

Prior to LLMs, it was amusing to consider how ML folks and software folks would talk passed each other. It was amusing because both sides were great at what they do, neither side understood the other side, and they had to work together anyway.

After LLMs, we now have lots of ML folks talking about the future of software, so ething previously established to be so outside their expertise that communication with software engineers was an amusing challenge.

So I must ask, are ML folks actually qualified to know the future of software engineering? Shouldnt we be listening to software engineers instead?

This is awesome! Love the work the charm bracelet team is doing.

If you say "china" to any of them, you'll see how very true your words are.

Where did TCP/IP come from? It's on every computer.

"there is no such thing as general intelligence, natural or artificial" - Alison Gopnik

one hasnt fallen behind when those in "front" are on the wrong path

The author is an intern, but they're also almost done with their PhD. They're not just any intern.

No, it wont. This comment essentially says science doesnt matter for anyone, only whether or not they're leading in marketing.

Apple's paper said a bunch of folks with weird predictions are wrong and so obviously lots of bad information will emerge in response. Who says what matters more now than it used to.

fair point!

Worth looking at how many papers the authors have published before assuming they challenge Apple.

just code and math either

this is literally what they are

fwiw, i dont mean to suggest AI is pure noise or even that AI isnt worth using. the report just doesnt reconcile with my experiences at all.

my experiences range from helping design penn's new AI degree programs, hearing from friends at algorithmic hedge funds, hearing from friends at startups, and my own development.

Because it is much higher than 25%

25% of developers 1 in 5 AI-generated suggestions estimate that contain factual errors or misleading code.

I cannot believe what's said in the report because it doesnt even reflect what my pro-AI coding friends say is true. Every dev I know says AI generated suggestions are often full of noise, even the pro-AI folks.

No. Printing presses were used for news well before then. That's why Franklin wrote what he wrote in 1731.

Here is Ben Franklin addressing this issue back in 1731 by essentially saying, "that's true, but then how would news ever get printed?"

https://founders.archives.gov/documents/Franklin/01-01-02-00...

I'm curious to understand the nature of what you're working on better.

Whether or not AI performs well is influenced both by the work you're doing and how experienced you are in it. AI performs better when the work is closer to mainstream work than novel work. It also performs better with lower level instructions, eg. being more specific. As for experience, there are two things: people with less experience get a bigger lift than those with lots of experience, or people wiht lots of experience get a lift by having AI doing the work they don't want to do, which is often unittests and comments or writing the bobdyllionth api endpoint.

I read your post the other day and appreciated the optimism, but I wasn't able to work out what kind of work you've been doing since leaving Sentry.

even at the highest levels of skill, it's not just a juniors-only phenomenon

AI has the most effect for people with less experience or low performance. It has less of an effect for people on the high end. It is indeed closing the skill gap and it does so by elevating the lower side of it.

This is important to know because it helps explain why people react as they do. Those who feel the most lift will be vocal about AI being good while those that don't are confused by anyone thinking AI is helpful at all.

It is not common for people on the high skill side to experience a big lift except for when they use AI for the tedious stuff that they don't really want to do. This is a sweetspot because all of the competence is there, but the willingness to do the work is not.

I have heard Dr Lilach Mollick, dir of Pedagogy at Wharton, say this has been shown numerous times. People who follow her husband, Ethan, are probably aware already.