Hacker Newsnew | past | comments | ask | show | jobs | submit | Kevin09210's commentslogin


I didn't take a very deep look yet, but this might be similar to https://github.com/pfeodrippe/recife


Until your prompts looks like the following:

<Do something> with the following text:

<some text>


Here are my experiments in this domain concerning complex interaction between the plane of narrated action and the plane of narration, i.e. having characters telling you stories ... within stories ... within stories.

But stories you can interactively drive nonetheless, as if you were in their shoes, while you listen them tell you what happens in reaction one narration level above. You can even argue with the narrator about what really happened rather than act in the story they tell.

https://pastebin.com/fK07dNhD


-----------------------Player input ---------------------------

//"Nah, Ol Rythm, I know Nancy story's by heart, this isn't what happened. It wasn't a sandstorm in the desert. It was a rainstorm in the jungle. You're mixing up everything in your boozed up mind bro"

--------------------------------------------------

Level 0: Ol' Tales – Player Challenges Ol' Rhythm "Wait, hold up," you correct Ol' Rhythm with a playful jab, "You're mixin' up the stories. It wasn’t no desert – it was the jungle, man. Rain pourin' down thick as mud, not that scorchin' sun and sand. You sure that whiskey ain’t messin' with ya memory?"

Ol' Rhythm throws his head back and laughs, a deep, belly rumble. "Aight, aight, you got me. Maybe I did have one too many. Alright then, the jungle it was," he concedes, his grin acknowledging the mix-up. "Nancy's convoy was knee-deep in a downpour, visibility nil, the whole deal. So there they were..."

Level 1: In the Jungle – The Convoy Encounter "...mud up to our axles and water pourin' down like we’d angered the gods," Nancy's voice takes over, now steeped in the greens and browns of the jungle, a torrential rain replacing the arid breeze, "And just when we thought it couldn’t get no worse, we heard it over the rain – the distinct chatter of AKs. We were about to have company, and they weren't there to share umbrellas."

Your eyebrows shoot up in intrigue, and you lean in a little closer, the bar around you fading into the shadows of a rain-soaked jungle on the edge of chaos. gpt-4-1106-preview using 2392 tokens ~= $0.030120


You need to get rid of codebase ownership and find something else to replace the trust it brings.

- Fine granularity forkability. Fork functions, not just projects

- Curators/Reviewers who endorse the validity/security aspects of those forks.


>Fork functions, not just projects

I'm not dismissing your idea, but I'm not finding the value in this compared to copy-pasting that function.It'd also be beholden to all kinds of dependency checking to be practical unless it was a tiny function.

But i can see the benefits of granular ownership. You don't necessarily want to fork off a whole new repo just to have a contributor be responsible for a module but not the entire project.


Daniel Promislow ?


I have not a single bad thing to say about Dr. Promislow, I never studied under him in graduate school and only worked loosely with him in undergraduate research. I also played a lot of music with him back in the day. If you are trying to sleuth my CV you are looking at the wrong school entirely.


That's superficial and bordering on ad-hominem.


When your work is as a scientist, and you want to be judged as a scientist, your work being pseudoscience is not superficial. That's like saying pointing out your accountant is facing tax fraud charges isn't germane to his work as your accountant.


What qualifies Loeb's work as pseudoscience (which is different from erroneous science as pointed out in the paper and blog post he reacts to) ? The thematics he chose to explore. He could have worded his paper differently, totally burying the extraterrestrial tech hypothesis he had in mind and there would have been no repercussions. Your opinion is driven by the semantics of the topic at hand and its success relies on the fact it fits into two heavily imbalanced classes. Of course I can go around and tell people they don't have that super rare disease: that doesn't mean I'm not a crank too.

Still waiting for you to delve into the details of the argument against Loeb's claims rather than using broad and easy categorization (which etymologically means accusation).


No one owes you an explanation, you're not 'waiting' for anything. You approve of Loeb's crank turn of late, that's fine, but you don't get to waste the time of others on demand.


fuck you I think Loeb is wrong, but you're just dumping your shitty easy opinion without putting forth any argument.


Well, I can't load the workflow. Installing the missing nodes requires restarting comfyui and it seems persistence on comfyworkflow's cloud isn't guaranteed anymore.

Also this website is pure single-page garbage. Everything is super slow, can't ctrl+click on a link to open it in another tab, etc ... An UX nightmare.

Can you recommend a competitor ? Looking at:

- https://www.thinkdiffusion.com/

- https://rundiffusion.com/comfyui-workflows

- https://flowt.ai/


I get similar results on thinkdiffusion



Not sure I'd call that "insane quality", more like neat prototypes. I'm excited where things will be in the future, but clearly it has a long way to go.


Or maybe the intelligence is in language and cannot be dissociated from it.


>“write X in the style of Y”

"Write this proof in the style of a program"

I think there is something a lot deeper behind this


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: