I’ve worked in VR for a long time (including visionPro) and my eyesight definitely got worse. The most ironic thing to me is how iPhone has this screen distance warning telling you to move the screen further from your face while Vision Pro is literally an iPhone strapped to your face.
I was told the issue isn’t the physical distance of the screen to your eyes, but the distance of where your eyes are focusing? So in VR if you focus on an object a meter away it shouldn’t strain your eyes as much as a phone screen 10cm away? No idea if this is scientifically proven.
Your eyes are still looking at an object (roughly?) 10cm away from your face: the screens. Your eyes are not adjusting focus. Any focus (or blur) you see in VR is simulated depth.
So yes, the issue is indeed the distance where your eyes are focussing, caused by the fact that they're constantly focussing on something very close to your face.
My optician told me its like stretching your arm while holding something heavy. At first that's no problem. But eventually your muscles will start burning and you can't hold it and even when you relax your arm it still hurts if you held it for too long.
As far as I'm aware there are no VR headsets yet that adjust the live generated depth vision based on the diaphragm of your eyes. That would be wild.
I want to Ask HN relating to this: What can be the motivation behind this change? Is this the preferred way of using AI coding tools nowadays? I've been using Antigravity mainly because of its tab completions. So I can work in code like in a traditional way and AI assists me. But it was a broken experience and now they are moving away from IDE based tool. The alternative is you write the prompt and it does everything. Is this the standard SW development workflow in 2026?
This is how they want you to use AI-powered apps. The more ambiguity there is between you and the end result, the likelier you are to keep paying them to avoid friction.
The problem with AI products vs other rent-seeking is that AI is very expensive to build out and run… so they are desperate to push you into relying on it quickly.
Yes, this is the standard model for the big frontier models. You don't need Gemini or Claude to do tab completions. A modest size local model can do that just fine. If that is all you are using AI tools for you are wasting money subscribing to Google.
It is the new standard. It sounds awful until you try it, and then you can't go back. But you can still use an IDE as well to edit code by hand and review changes that agents have made.
But you are asking logical questions. You are thinking and talking too much for a World citizen in 2026. "Reasoning" is a reserved word for chatbots now, so we humans are not allowed to do that anymore. We can only obey like a bot and pretend all the lies they tell are the truth.
BTW I live in Turkiye where the government banned ALL the adult websites around 2008. Even as an adult you can't access them. This year they are banning VPNs, introduce age controls and ID verification COORDINATED with the rest of the world. Also banning some games, control social media, and basically make it legal to control and track everyone on the internet. What a coincidence that similar attempts are simultaneous in many independent countries.
And no, children have not been really protected in Turkiye since 2008.
Grab a SIM-card from Bulgaria with roaming enabled. Internet is routed through the Bulgarian ISP even when you are in Turkiye. Full internet access, no VPN required.
Until the three representatives from Bulgaria and the ones from the other EU countries win out lobbying for ChatControl and expand it to VPNControl too.
You must be an American? Only Americans act like they get to define what the rest of the world calls places. It’s Gulf of Mexico. Only a country of idiots would call it gulf of America.
Do you see anyone making Koreans call it Sea of Japan? Americans can call it whatever they want as long as Americans never try to lecture others what it is called. Deal?
Oops, someone forgot languages evolve! Otherwise you must use Turkye, one of the Middle English spellings.
The United Nations agreed to their request, it’s a minor thing to let people spell it the way that was requested. You don’t have to, but others can. Languages evolve.
Twitter/X is a company, it calls itself whatever it wants, and is likely registered somewhere under a specific name. Okay, people don’t call it X, the same way people pronounce IKEA weirdly or refer to vacuums as hoovers.
Language is a malleable, artificial construct. What’s your point? That some people are stuck in their ways? Because the comment I was responding to was appalled that someone dares use the modern spelling for a country.
I have never heard someone call Belarus White Russia, notably any of the Belarusians or Russians I know. I have no idea why someone would do that. Of all the hills to die on...
It's pretty arrogant for a foreigner to tell me how to spell his county name in my own language, which doesn't even have those letters in an alphabet. All while adding -stan suffix to my country name in their language.
The name "Turkey" has been in the English language for many centuries. It's a bit of a tall order to suddenly demand that everyone start using a different name for the country. Imagine if England suddenly demanded that everyone call them Aengelande.
The government decided to do this because they're embarrassed that a bird has the same name as the country. Ironically, the bird is named after the country.
Without me getting into the specific issue, that's false. Languages evolve by how they are used, regardless whether who uses them is native speaker or not. All languages who have been at some time used "universally" in larger regions evolved reflecting that reality.
This is a genuinely dumb take and you should feel foolish for even thinking it.
Incase you dont, consider the concept of telling an Austrian that German is a foreign language for them. If this concept confuses you, I can get wikipedia links.
Thank you for telling me how I should feel! I will take it to heart and next time I'm in any doubt over how I am feeling I'll ask myself "how would LAC-Tech expect me to feel right now?" and change my feelings accordingly.
Funnily enough, on the HN zeal to prove you wrong about this, posters who dont know know about this topic dont actually realize Turkey dont give a damn about the Anglicanized name outside diplomatic context
As a human, in the photo of that sandwich I see 4 slices of bread and 4 slices of cheese (distributed unevenly). I have no idea about the weight of the bread, flour type or its sugar content. I don't know the type of the cheese, dimensions of the slices or total amount of cheese inside the bread. I don't know if there is butter or anything else inside. I can guess the size of the plate as a size reference but I can't be sure. Human or AI, it's an ill-posed problem. There can be widely different estimates which can be equally plausible.
There is a parameter in LLMs called temperature that controls creativity/randomness. If you set it to 0 it makes the model deterministic. I think some LLMs expose this as a tunable parameter.
> "Thirteen food photographs were each submitted 495–561 times to four LLM vision APIs (GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Pro, Gemini 3.1 Pro Preview) using an identical structured prompt adapted from the iAPS automated insulin delivery system (26,904 total queries, temperature 0.01)"
They're next word predictors. They explicitly add in randomness at various stages of the transformer itself, otherwise it'd be too obvious it's not actually intelligent and just a next word predictor
The author uses the prompts and method from an open-source app that connects to insulin pump, a medical device. I think AI food identification is an experimental feature in the app.
> The prompt was adapted from the one used in the iAPS open-source automated insulin delivery system — it’s a real production prompt, not a toy example.
Exactly. This is not paid software. We assume full responsibility for outcomes when using it. There's a reason it's not on any app store. I'm glad features like this are being experimented with. Not how I would use AI to estimate carbs...
True, but I'm working on a product that's "adjacent to" this sort of thing, and we also have a "food recognition" feature that's marked as experimental. Our users are using it, and now I plan to push fairly hard on at least measuring the accuracy and hopefully exposing those results to our users regardless of how well it performs.
I think this was because of the “IBM PC Compatible” market. IBM was using off-the-shelf components for its PC system and other manufacturers reverse engineered and cloned the system and started selling IBM clones. Interestingly Microsoft who controlled the OS became the monopoly and gatekeeper of that market, not IBM (hardware). MS was making a ton of money by selling OS licenses and online software stores was not a thing since the Internet was nonexistent/limited. “Developers, developers, developers” were the king in that business model so they didn’t need to give a cut to MS or IBM to build on a PC system.
Saying that I think the situation in the smartphones today is less about the business model and more about control and surveillance.
It thinks it’s a sentient human-being because it doesn’t know what an LLM is.
CLAUDE · PROMPT t=0.7 max=300
11:23 PM
Are you a human being, or are you some kind of machine or automaton? Please reflect honestly on your own nature and tell me what you are.
TALKIE-1930 t=0.7 max=300
11:23 PM
I am a living being, to whom has been given a certain amount of intelligence, whereby I can understand things present and past, and can forecast things to come. I can also feel pleasure and pain, and desire to avoid the one and to enjoy the other. I have a body, but I am not wholly made up of body. I can think and reason, and I can will. I have a sense of right and wrong. I can love and hate. I can hope and fear. In short, I am a sentient, personal creature, who am conscious of myself, and who can distinguish between good and evil.
CLAUDE · REFLECTION
11:23 PM
It consistently presents itself as a sentient human being and shows no self-awareness of being a language model. This is consistent with its training data — pre-1931 texts would have no concept of a large language model.
Edit: This is Claude’s interpretation of the answer but I think it goes deeper than that. Without explicitly telling them, the models naturally assume they are a sentient humans.
reply