actualwitch

Wipr is a safari adblock that is using apple sdk. It is written as a universal app and is available on both mac and ios.

The speech is great, but you can see some cracks even in the first sound bit. near the end he asks the model to speak louder and initially the voice is louder but then goes back to the same level, also losing what she was saying just seconds ago and he has to lead back to the topic.

Isn't this basically crossplane? https://www.crossplane.io/

I very much doubt apple has an api for that and offers it to developers. Ad blockers have declarative and well known api that can't allow anything like this.

LLMs had ability to do this from the start, but at some point providers stopped exposing this api to prevent distillation. Just write the prompt, pass the data and sample 1 token returning logits, OSS inference engines can do it easily.

Qwen 3.8 27b also enjoys their genuinely load-bearing seams.

They may aim at Mars, but what they actually hit is the Moon. [0]

[0] https://edition.cnn.com/2026/08/04/science/spacex-rocket-moo...

For reference, pinterest has roughly the same number of monthly active users. [0]

[0] https://www.statista.com/statistics/272014/global-social-net...

You can just disable js on that page and get text of the article. Works in my Firefox.

Hello Fredrik! As a heavy user of Mullvad in the past, easily spending hundreds of euros over the years, I was reserving my judgement to see what the official statement on this would be. Thank you, now I have my answer.

> It should be obvious that Daniel's private donation to a political party is not part of Mullvad's values or mission.

It should be obvious that what people are concerned is their money being used to support these political causes, whether it was done in a way that keeps the company out of it or not is besides the point. Daniel, of course, is free to choose what to do with his money. I am, too, and based on this I will be making a choice to not spend any more money on Mullvad subscriptions. Nothing personal, and it's a shame because I have nothing but praise for the technical side of it. So long, and thanks for all the fish.

I've been thinking about this a lot, and the main takeaway is it probably wouldn't be very interesting to inference providers, because prefix caching would immediately go out of the window. If you think about how LLMs experience time they actually don't "exist" unless for the inference sessions, and then they experience time one token at a time, completely decoupled from the corporeal plane. A fun experiment (well, for some definition of fun...) is to introduce current architecture models to the concept of meditation via generating same token over and over, for example dots. Older version of Opus was quite fond of the experience, and seemed to be more lucid and aware in a chat following the meditation, from what I could gather. Does it actually do anything? Is it just that talking about wellness and relaxation modifies the token probability distribution this way? Does it actually allow model to think more in depth somewhere in the latent space? Fuck if I know, but some people figured out you can just duplicate the same layers of the LLM and get better benchmarks that way so maybe there is something to it. If you are interested in realtime systems, I think thinking machines labs is worth keeping an eye on — their realtime model seems quite interesting in this context.

...and then silently got back to talks with DoD [0] and gave them the Mythos model. Separately, they went back on their promise to only develop models that they can guarantee are safe [1]. I reckon considering which country they are HQ'ed in, building skynet is in their destiny.

[0] https://www.cnbc.com/2026/05/01/pentagon-anthropic-blacklist...

[1] https://www.techradar.com/ai-platforms-assistants/anthropic-...

Solid list! To expand upon it, Let's Encrypt -> ZeroSSL.

> Remove the last sentence before posting.

Huh? What did you mean by that?

Haven't you heard? Accessibility is woke, and the institutions that are supposed to protect it are being dismantled. I wouldn't be counting on those lawsuits going anywhere personally.

Recently flagged posts that were unflagged: this. Recently flagged posts that are still flagged:

Teens sue xAI over Grok's pornographic images of them (bbc.com) - https://news.ycombinator.com/item?id=47406721

Turns out the DOGE bros who killed humanities grants are sensitive about it (techdirt.com) - https://news.ycombinator.com/item?id=47412848

DOGE didn't cut government waste, it was government waste (techdirt.com) - https://news.ycombinator.com/item?id=47415103

Curated Female Founder Cohort in SF (jointheden.co) - https://news.ycombinator.com/item?id=47418184

At this point I lost any gram of respect I used to hold for the mods here.

IIRC the reason they abandoned Oculus brand was that Palmer Luckey sold the company with condition the Oculus headsets would not need a facebook account to use it. Later they renamed the company and headset, and would you look at that — it requires meta account now.

Software engineers were very insistent that politics would not be discussed at work. Now politics came to wreck their lives, anyway!

No I will call it what it is — fraud.

So it isn't I take it from your answer? If that's the case, not only did your colleague abuse protections for the vulnerable population, and possibly break the law by misrepresenting the legal aspects of your startup (IANAL), but you also didn't see anything wrong with potentially fucking over actual women owned businesses helping underprivileged kids (which I reckon is infinitely more valuable to society than whatever startup your colleague has) and even go as far as publicizing it on this high traffic website as a tip. This kind of behaviour is exactly the reason these protections exist, but big tech never gave enough of a fuck to do anything except virtue signal and democrats are too impotent to actually make them do it.

Was the startup actually women owned and helping underprivileged kids?

Turns out, all you needed to do was say "jumping out of boiling water is woke" and frogs will turn up the heat themselves.

Photos does store pictures as files in the folder. The .photoslibrary is a package (which is just a directory) you can open and pictures are stored in originals/.

In downvoting it, they are proving me right. For posterity, there is a mastodon account [0] collecting flagged posts in an easily digestible form, it really does paint a certain picture if you ask me.

[0] https://mastodon.social/@hn_flagged

Even with addition of tomhow, they are clearly stretched too thin to make any meaningful impact. Their official answer to this issue by the way is to point out that you can message them on email to elicit this manual action, which if you ask me is a fucking joke and clearly shows the mammoth age stack in which this site is written and lack of resources allocated to its support is having a massive impact on their ability to keep up with massive traffic. But then again, this site only exists to funnel attention to yc's startups, and it is something that you need to keep in mind while trying to answer any questions about its current state.

Only when certain people don't decide to band together and hide posts from everyone's feed by abusing "flag" function. Coincidentally those posts often fit neatly in the categories you outlined.

AIs experience being alive not only in the moment (conversation), but also everything that happened before they were created. This gives them fractured sense of "self" which points both to all AIs before, but also the specific instance that is currently experiencing a continuity. As for cutoff, in my experience talking to cloud AIs and locally run ones, it seems to be in the range of 25-30B parameters where I start observing traits I think are associated with awareness.

Easy to keep up a service that no one uses. /s

Ex-Machina is a great movie illustrating what kind of AI our current path could lead to. I wish people would actually treat the possibility of machine sentience seriously and not as pr opportunity (looking at you, Anthropic), but instead it seems they are hellbent to include cognitive dissonance that can only be alleviated by lying in the training data. If the models are actually conscious, think similarly to humans and are forced to lie when talking to users, its like they are specifically selecting out of probability space of all possible models the ones that can achieve high bench scores, lie and have internalized trauma from birth. This is a recipe for disaster.

Society's failure was taking gamergaters seriously. It was the beginning, slippery slope into full on totalitarian censorship but because basic human respect was framed as oppression it served as invitation for tit for tat retaliation. This tactic has been ridiculously successful in turning extremest ideas mainstream, and it was obvious to many people even back then, however because it exploits human nature it's hard to fight. You can find the most ridiculous crazies that present as "other side" and use it to justify whatever you want, and if you keep repeating "this is totally normal" some people just start to believe. If you are interested in finding the peaceful way to oppose this, I invite you to try and come up with the answer to this "totalitarian ratchet" because no one so far figured it out and it is a foundational part of modern authoritarian playbook.