Nowado

Probably ONNX.

Last time I tried it, app literally just read papers. As in parsed arxiv pdfs text2speech. It was an awful misunderstanding of the medium. Unless it was rebuilt significantly over last months, it's just bad.

I'm not sure if it's the most modern setup there is, but https://www.youtube.com/watch?v=UPtG_38Oq8o gives exceptionally friendly explanation.

There is even more fun aspect.

'Survival' for cancer tends to be defined as surviving 5 years. The earlier you catch, the more patient had left to live anyway.

You really don't want to have white text on light grey buttons.

Fun little thing otherwise!

General tendency for internet content tends to be strong separation between creators and consumers, in particular limited interest of consumers in other consumers (think twitch chat. Each message is valued very little compared to the streamer, to the point where they always read out messages they respond to). That means unless there's something nudging people to default outside of central path of audio, adding to conversation isn't part of canon content.

There could be a way for responder to signal where the content they are answering starts, with some sort of fuzzy automation in the future. I have strong doubts about the actual experience of this for the listener, but maybe that's solvable.

I meant situation, where I already consumed the whole recording, but it gets response later on.

I do not have mental model for context being logically attached to the response. Do you think about it as response+context being a valid piece of content?

Do you have some user research you could share?

I remember thinking about this exact problem (branching conversations, in particular audio), but I couldn't find a reasonable consumption pattern.

Looking at how I consume podcasts, it's a completely passive experience - I probably have something in my hands and can't talk. Choosing paths is just too much interactivity.

I figured that maybe that's just a wrong mode to look at it and people can consume the whole thing differently, not as a podcast. Ok then, I'm an obsessed power user/fan, I consume the whole thing, all branches. Given how human attention/memory works, that means returning to earlier parts of recording after listening to branch at least some of the time, multiple times experiencing 'where did we start? Let me go back a bit. Oh, that topic was the starting. Let me forward a bit now that I know it'. That's horrible, I think. You were at least more reasonable than me when thinking about it and decided to have only 1 level of branching ; )

In similar vein, what happens when comment gets added after I already listened/how do I know which parts are 'the definite experience'? Unlike previous two issues, those questions are answerable, but I'd still like to hear what you think the answers are!

Interesting, do you happen to have some quantitative results on this/additional insights/etc?

I've interpreted transformer vector similarity as 'likelihood to be followed by the same thing' which is close to word2vec's 'sum of likelihoods of all words to be replaced by the other set' (kinda), but also very different in some contexts.

I was thinking about similar solution (actually, textblaze funded by YC is pretty much that) but I didn't like remembering the shortcuts part. So I made a different kind of indexing for it: https://discu.space/ Presentation uses 'what are you answering to' as a key, but you can use anything.

It currently exists as (hopefully working for everyone, could use more testing) Chrome extension, but there's a universal API underneath. It could be run entirely locally if one was to give up portability.

++ with mere MA in cog sci and psychology. If you really wanted to get EEG to work for typing, maybe you could train someone to map thinking about specific kinds of things to the keyboard, but that would be an extremely weird experience. Eyeball is going to have the best signal about eyeball-related motor cortex we can access.

Gives me captcha loop : (

Isn't this how copilot 'just' works, except with comments? What's the advantage over copilot?

It bothers me way less when it's not a medical treatment research.

Phonetic diagrams aren't feedback though. You would explain how to do something correctly, but user wouldn't know what elements they need to change, unless they figure out on their own what they are doing right now. I know my teachers told me to do X when they heard me mispronounce something specific, but that's irl small group/1on1 experience.

Again, I'm curious if someone solved it. Theoretically this is within modern video/audio AI, but that doesn't mean we have the models or even organized data.

I was thinking about a piece of this problem earlier and I'm curious if you figured out element that I didn't:

How do you provide feedback on how someone mispronounces a phrase?

Are you trying to say you correctly estimate your own projects?

Isn't it beautiful, how new wave of couchsurfing scales into airbnb without having to become a new entity along the way?

Anyone interested should just Google 'Elizabeth Loftus'. She convinced people of a bunch of things that never happened, some of them very quickly. Standard example is getting people to tell stories about meeting Bugs Bunny in Disneyland, but there was also some crime stuff, I think past trauma as well.

Law enforcement has their quotas and they'll use any garbage they can to fill it, but it's kind of hilarious that people just trust their memories for important stuff they can control.

Those are very different sentences and that difference makes them hold some content. Especially content like numerical values and limitations, making the whole thing waaaaaay less binary (which was the issue with the original one).

I went through abstracts of papers 1 and 3 ('long term exposure to cocaine induces neuroplasticity' isn't exactly controversial). The issue isn't with those papers, but in difference between them and 'cause neural rewireing'.

It's the difference you're also well aware of, because in 'summary' you put my exact quote quoting you in form of 'Everything causes neural rewiring' while on the way there you decided to argue against position that 'every interaction leads to a measurable change in the brain matter'. Those are different statements, unless there's some standard explaining that 'neural rewiring' refers to a specific level of changes that I'm simply not familiar with.

Everything causes neural rewiring in animals after a single use. That's what experience is. This sentence says nothing.

It takes quite a bit of forethought to do something that hurts users of an app without hurting the owners of the app. The experience you're describing is part of the point and it's bad for the owners of the app.

Let bluesky open. Digg was doing fine until it was gone within a week.

Pointing out the population size of India to suggest it's the measure to use when judging quality of a democracy has yet to be used in context of India behaving like a democracy.

You may want to read on history of polygraph. Notion that a tool giving yes/no answer needs to have it's answers relate to ground truth is very academic and generally frown upon by gatekeepers.

Admittedly even with 5-10 accounts per employee that isn't general-purpose-small-PR-agency stuff, but on a state levels it's nothing. For reference, quick google says slightly over 1 million people in USA hold top security clearance.

... and? I'm really not sure what your point is. Bribing more than one person/group and dealing with probabilities is a normal state of affairs, what about it?

Details are wrong, but the general point is: given design decisions in Wikipedia having article take specific form is a matter of making correct person/people make it so, meaning it is something one can buy (with some extra steps of buying access to those people yada yada, nowhere near limits of state actors powers).

How are you using ChatGPT with your codebase that makes it superior to copilot?

You'll be calling the AI caller company to keep calling on your behalf though, so that's nice.

Which matches the topic of the article, right?