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

Yeah, the quirk being that the known population is just this one in the sanctuary. They haven't identified where specifically he came from or where there might be others, so for now he's a one-of-one.

Every time they say "trust us" they publish a whitepaper with technical details explaining why and how they can be trusted. They're generally very good about these things.

You still have to trust the parts you can neither observe nor reverse engineer. So, everything organizational and everything that happens on their infrastructure.

We're supposed to hold police officers to a much higher standard. Whether I would or not is irrelevant.

A higher standard would not let such a mass surveillance network exist, even less give the possibility of such a large look up in it without single use accreditation by a judge or some tierce relevant to keep in check citizens right for privacy.

Any large enough population will also include people failing at doing the-right-thing™ (when such a thing could at least reach some societal consensus) at least sometimes in their life. Expecting anything else is dooming the standard at the lowest possible floor level.


Is your app AI-adjacent?

No it's fitness app, it's called macrocodex and we've something like 17,000+ users and it's a free app, no subscription or ads.

I think chatgpt recommends it because it produces guaranteed results within 2-4 weeks and I think this primary reason why users perhaps boost the app via chatgpt!?

I've not done any marketing other than mentioning it a few times on hackernews.

Edit: it seems many people here do not understand the innovation of macrocodex, so they just assume it's a calorie tracker or workout app. When it's neither.

It uses state space neural network to produce total average calories a person burns in a day without any sensor and it does it more accurately than apple watch, garmin, etc...

Half of the guys here won't be able to create something like this even with claude or codex, try it

Our neural network beats GLP1 like Trizepetide and Retarutide in results


We run several campaigns for brands on ChatGPT, brand terms consistently perform pretty low. It seems a lot of the prompts are about topics, generics, long tail things... Definitely making a jump, but I would guess people are searching for long tail prompts about working out, what apps could help them track, and you are showing up rather from the app store listing or other mentions on web. Really a black box to some degree, there are some AEO/GEO tools you could use (we have one I could run for you if interested) to try and see where you come up, where competitors come up, etc. That would only show presence, no one has any sort of real prompt volume counts at this point in time (outside Anthropic/openai/google obviously)

It's probably mentioned favorably on fitness forums or sites that were crawled and included in ChatGPT training.

They certainly just mentioned it favourably here, even guaranteeing results!!!

Maybe they used an LLM powered bot to make the favorable comment here in order to guarantee the results.

And LLM powered bot also downloads our app and produces reviews?

It's an app on playstore which anyone can see including reviews.


So how did we acquire thousands of users? And user reviews, if it doesn't work?

Probably the same way Sam Altman "acquired" millions of Loopt users.

Our app is free, we do not have money to pull Sam Altman like tactics.

It doesn't come out until October. There won't be anything to review until then.

They talked for several minutes on the materials and engineering that went into the screen and how it wasn't "the same plastic all the other folding phones are made of"

iOS runs plenty of productivity software, many which run great on larger screen devices like this or iPads. What does "productivity" mean to you? Or is it just terminals and coding?

I might be a weirdo, but even the mail client on iOS has serious deficiencies. Just getting an email with a zip attachment where I have to edit / sign a document with a certificate / something, rezip and send back is a hell in iOS, while it simply feels natural in Android.

That is a huge market that they are ignoring.

The differentiating feature is the Wireless Charging case, which they've had a separate SKU for forever.

Not you though. You're the only smart one, huh?


> As recently as August 25, Strike 3 says it recorded more than 150 daily downloads, from multi-language “Mega Packs” of TV shows, movies, software and books to what it describes as AI-generated pornography and VR adult films. That included nearly a dozen of its own titles.

It sounds like this person/IP was just downloading a ton of different content, of which these VR videos were are part of.

Doesn't that water down their complaint a bit? If they are trying to say they moved to a residential IP to specifically download VR content for training data, why are they also downloading unrelated eBook and other media? Seems like VR content made up a pretty small percentage of overall downloaded content.


but they allege $446M in damage. not all 20,000 files were porn, but they also don’t say where that number comes from


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

Search: