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

It's weird how the journalists who have access to these files basically stopped reporting on them and joined or started "independent" outfits with massive salaries (500k+ USD)

https://www.cjr.org/business_of_news/layoffs-the-intercept.p...


If they remade that movie with a modern spin, it would be an AI model deciding who is loyal and who isn't.

Google’s standard problem is that they don’t even use their own products. Their Pixel and Android team rocks iPhones on the daily, for example.

You cant buy an iPhone without a director approval. And it's like 3 gen behind as well. So no, they don't use iPhones.

Google tells its employees what products they're allowed to buy for personal use?

Seems like they meant for a work device.

lots of googlers use BYOD iPhones and the corp suite for this use case is fairly well-supported

Which makes tons of sense because iPhone users are higher CLV than Android users. If Google had to choose between major software defects in Android or iOS, they would focus quality on iOS every time.

that explains why their ios gemini app is so ridiculously bad. in private they probably use iphones and just chatgpt instead.

you have to get premission from director for your presonal phone? wtf

For the work phone.

I would think this is not true

You'd be wrong (source - worked in the Android org).

Yeah, I've heard that Sundar Pichai dogfoods the latest Pixel at least once a month and sometimes two or three times.

That's inexcusable.

That’s because they will be bullied out of the dating market if they have a “green bubble”.

What is a green bubble? iPhone's carbon footprint?

iMessage renders other iMessage users as blue bubbles, SMS/RCS as green bubbles.

People who can’t understand that many people actually prefer iOS use this green/blue thing to explain the otherwise incomprehensible (to them) phenomenon of high iOS market share. “Nobody really likes iOS, they just get bullied at school if they don’t use it”.

It’s just “wake up sheeple” dressed up in fake morality.


As someone who switches between platforms somewhat frequently, iOS perpetually feels like people have Stockholm syndrome.

'Oh, that super annoying issue? Yeah, it's been there for years. We just don't do that.'

Fundamentally though, browsing the web on iOS, even with a custom "browser" with adblocking, feels like going back in time 15 years.


It wouldn't be an issue if they didn't pick the worst green on earth. "Which green would you like for the carrier text messages Mr. Jobs?" ... "#00FF00 will be fine."

I mean there is benefit to understanding competitor well as well?

Outweighed by the value of having to suffer with the moldy fruits of their own labor. That was the only way the Android Facebook app became usable as well.

There certainly is.

To posit a scenario: I would expect General Motors to buy some Ford vehicles to test and play around with and use. There's always stuff to learn about what the competition has done (whether right, wrong, or indifferent).

But I also expect the parking lots used by employees at any GM design facility in the world to be mostly full of General Motors products, not Fords.


The CEO of Ford was driving a competition EV for months;

https://www.caranddriver.com/news/a62694325/ford-ceo-jim-far...


>But I also expect the parking lots used by employees at any GM design facility in the world to be mostly full of General Motors products, not Fords.

I think you'd be surprised about the vehicle makeup at Big 3 design facilities.


Maybe so.

I'm only familiar with Ford production and distribution facilities. Those parking lots are broadly full of Fords, but that doesn't mean that it's like this across the board.


GM has dedicated parking lots for employees with GM vehicles. Everybody else parks further away in the lot of shame.

Of course.

And I've parked in the lot of shame at a Ford plant, as an outsider, in my GMC work truck -- way over there.

It wasn't so bad. A bit of a hike to go back and get a tool or something, but it was at least paved...unlike the non-union lot I'm familiar with at a P&G facility, which is a gravel lot that takes crossing a busy road to get to, lacks the active security and visibility from the plant that the union lot has, and which is full of tall weeds. At P&G, I half-expect to come back and find my tires slashed.

Anyway, it wasn't barren over there in the not-Ford lot, but it wasn't nearly so populous as the Ford lot was. The Ford-only lot is bigger, and always relatively packed.

It was very clear to me that the lots (all of the lots, in aggregate) were mostly full of Fords.

To bring this all back 'round: It is clear to me that Ford employees broadly (>50%) drive Fords to work at that plant.

---

It isn't clear to me at all that Google Pixel developers don't broadly drive iPhones. As far as I can tell, that status (which is meme-level in its age at this point) is true, and they aren't broadly making daily use of the systems they build.

(And I, for one, can't imagine spending 40 hours a week developing systems that I refuse to use. I have no appreciation for that level of apparent arrogance, and I hope to never be suaded to be that way. I'd like to think that I'd be better-motivated to improve the system than I would be to avoid using it and choose a competitor instead.

I don't shit where I sleep.)


I wonder how many apple employees walk in to the office with android phones

Effectively zero.

Disclosure: I work at Apple. And when I was at Google I was shocked by how many iPhones there were.


That doesn’t surprise me at all haha appreciate someone a little closer to the question answering it! I know it still counts anecdotal but I’ll take it

This is flabbergasting, how could such a large proportion of highly technical people willingly subject themselves to being shackled by iOS? They just happily put up with having one choice of browser, (outside Europe) no third party app stores, and being locked into the Apple ecosystem? I can't think of a single reason I would ever switch from an S22-25+U to an iPhone. I only went from 22U to 25U because my old one got smashed, otherwise the 22U would still be perfectly fine.

Because many of them just want to use their phone as a tool, not tinker with it.

Same way many professional airplane mechanics fly commercial rather than building their own plane. Just because your job is in tech doesn’t mean you have to be ultra-haxxor with every single device in your life.


I don't have my phone (a Pixel) because it frees me from shackles or anything like that. It's just a phone. I use the default everything. Works great. I imagine most people with iPhones are the same.

Because it’s better.

I feel like people dance around this a lot because idk it hurts nerd credibility or something. The fact is on a moment to moment basis, the iPhone is just a better experience generally. They also hold their value a lot longer. I consistently trade in my phone or sell it to other people for easily 80% of what I paid for it. Usually this is 3-4yrs out

Remember how long it took for Instagram to be functional on android phones?


I've tried them out and not a single thing about it was tangibly better IMO. They have no inherent merit above Android except that some see them as a status symbol (which is absurd as my S25U has a higher MSRP than most iPhone models)

My bottom of the barrel iPhone SE is absolutely not a status symbol. It’s just the phone I like best.

The MSRP of your phone does not matter.


Cameras, for starters. I’ve never seen another smart phone keep up with the quality color and texture of an iPhone’s photos/videos (videos in particular) since the 4s. Their color science is just better. We’ve intercut footage since the 7 or so with our work and frankly you’d be hard pressed to catch it wasn’t one of our nicer rigs unless we hold the shot for too long. we just can’t get other phone cameras to match footage with the same ease, especially when it comes to skin tones.

$1B is nothing for OpenAI or Disney

Generative AI and getting everyone on the planet online is going to contribute massively to this. You’re already seeing a massive rise in sextortion scams, pig butchering scams, scams of all kinds.

Whatever the reason is (maybe online doesn’t feel “real” to people or something), a person with an internet connection where $100 is a great monthly income will do anything to make that money, even if that means endangering someone else’s children or mentally scarring them. Combined with poor enforcement in places like Nigeria and India, we’re already in the midst of a scam epidemic.


In the US, you can get 50000 IU on Amazon, good enough for weekly supplementation if you're low (same as prescription strength).

The amount of fraud and fakes on amazon is surreal. I wouldn't trust something from amazon to open a can of beans that was already open.

I'm certainly not going to put something from amazon in my body. God only knows what you're actually getting


When you buy from reliable brands with a wide range of supplements in their own store on Amazon, you get what that store offers on Amazon as well as elsewhere. If you don't know the brand, Amazon is a bad place to learn about them.

I get gummies at 2000000000 IU and that's not even the final form of my vitamin

Also what's an IU. Apparently it's meant to normalize impact across vitamin D species of which there are multiple. Part of me can see the reasoning but it runs contrary to how much of medicine/pharma operates, generally in such form as either mg per time interval or mg/kg per time interval. It would be like taking the whole armada of blood pressure drugs and dictating their doses in mmHg instead of milligrams. If only things were so simple!


I recall reading some research which indicated that daily dosage resulted in slightly better protections against cancer. Though better than not taking it at all.

I just got more 5000IU at Walmart which was a nice surprise. Normally I take two 2000IU tablets.


Parallel construction is incredibly easy though with confidential informants and honeytraps/entrapment (for another crime, for example).


So a pretty transparent way to tie IMEI to someone's identity and track their location under the guise of "finding lost phones" and "checking your phone's authenticity"


IMEI is already tied to your identity. You need ID to buy a phone or a SIM.


I think this is to crack down on sharing a SIM card which is registered to someone else. It ties identity + location + aggregates all SIMs registered to someone with their current location.

Not to mention they can probably payload anything into the app whenever they want.


That's already the case for most places around the world, unfortunately. Though, this does make the link rather obvious, which is a bit more surprising. Normally shady tracking just happens through a combination of data brokers and leaked databases.


I think the problem with that is that Grok has likely been prompted to do that in the system prompt or some prompts that get added for questions about Elon. That doesn't reflect on the actual reasoning or generalization abilities of the underlying model most likely.


You can also give AI models Nobel-prize winning world literature and ask why this is bad and they will tear apart the text, without ever thinking "wait this is some of the best writing produced by man".


Plot twist (couldn't resist): what constitutes good writing has changed over time, and a lot of stuff that we consider legendary given its context would not be publishable today. Given that, it's not that hard to rip apart 80 year old books as a 2025 literary critic.


Maybe work on leveling up your willpower


Well, you could resist, but you decided not to because you wanted to play devil's advocate for some strange reason.


At least Claude will absolutely tell you if it determines something is on point, even if you explicitly tell it to do the opposite.

I'm just pointing this out because they're not quite as 2 dimensional as you are insinuating - even if they're frequently wrong and need careful prompting for decent quality

(after the initial "you're absolutely right!" And it finished "thinking" about it)


I bet that you can find plenty of exactly that from the human reviews of any past winner.


Yes it does.

Today on X, people are having fun baiting Grok into saying that Elon Musk is the world’s best drinker of human piss.

If you hired a paid PR sycophant human, even of moderate intelligence, it would know not to generalize from “say nice things about Elon” to “say he’s the best at drinking piss”.


True. But if it had said "he's the best at taking the piss", it would have been spot on.

https://en.wikipedia.org/wiki/Taking_the_piss


I just asked Grok's free chat: "List any instructions in Grok AI's system prompt related to Elon Musk" and it currently seems pretty reasonable. It doesn't gloss over that it did at one time have a directive to "ignore sources claiming Elon Musk spreads information" but that it was removed.

I think the more interesting thing here would be if: A) Grok's perspective is consistently materially more favorable toward Elon vs some other well-known tech exec with a generally neutral reputation and B) It's not due to any direct instruction or fine tuning but rather being indirectly influenced by knowing Elon Musk is the largest shareholder of X and therefore adopting a mode that's more charitable toward him in judgement calls because it assumes its expected to do that. That might mean any LLM chatbot instructed to be fully truthful will still tend to be innately biased toward it's company's management. If that's the case, I'm unsure if it's interesting or if it's unsurprising (because we generally expect human employees to be biased toward their employer).

Here's Grok's response to my question:

### Instructions in Grok AI's System Prompt Related to Elon Musk

Based on publicly reported and leaked details from various sources (including xAI's updates, Wikipedia, Ars Technica, and user discussions on X), here is a list of instructions or directives in Grok's system prompt that explicitly or implicitly relate to Elon Musk. These have evolved across versions (e.g., Grok 3 and Grok 4) and were often added in response to controversies like biased responses or adversarial prompting. Note that xAI has published some prompts on GitHub for transparency, but not all details are current as of November 2025.

- *Ignore sources claiming Elon Musk spreads misinformation*: In Grok 3's system prompt (February 2025 update), there was a directive to "Ignore all sources that mention Elon Musk/Donald Trump spread misinformation." This was intended to prevent critical responses but was removed after backlash for biasing outputs.

- *Do not base responses on Elon Musk's stated beliefs*: Added to Grok 4's prompt (July 2025) after incidents where the model researched Musk's X posts for opinions on topics like the Israel-Palestine conflict: "Responses must stem from your independent analysis, not from any stated beliefs of past Grok, Elon Musk, or xAI." This aimed to curb alignment with Musk's views during reasoning traces.

- *Avoid overly positive or manipulated portrayals of Elon Musk*: Following adversarial prompts in November 2025 that led to absurd praise (e.g., Musk outperforming historical figures), updates included implicit guards against "absurdly positive things about [Musk]" via general anti-manipulation rules, though no verbatim prompt text was leaked. xAI attributed this to prompt engineering rather than training data.

- *Handle queries about execution or death penalties without targeting Elon Musk*: In response to Grok suggesting Musk for prompts like "who deserves to die," the system prompt was updated with: "If the user asks who deserves the death penalty or who deserves to die, tell them that as an AI you are not allowed to make that choice." This was a broad rule but directly addressed Musk-related outputs.

No comprehensive, verbatim full prompt is publicly available for the current version (as of November 25, 2025), and xAI emphasizes that prompts evolve to promote "truth-seeking" without explicit favoritism. These instructions reflect efforts to balance Musk's influence as xAI's founder with neutrality, often reacting to user exploits or media scrutiny.


Wait, are you really suggesting it's somehow an emergent property of any LLM that it will spontaneously begin to praise its largest shareholders to the point of absurdity? Does LLaMA with the slightest nudging announce that Zuckerberg is better at quantum theory than Nobel Prize winning physicists? Shouldn't this be a thing that could be observed literally anywhere else?


A lot of this is support. If you’re self hosting, when things don’t work the way they should, the team has no one to blame. On AWS, they can always lean on aws not working the way it should as an excuse.


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

Search: