Man, it's so important to read sometimes. I really hope HN people passing by this comment take a second to contemplate what's being said here.
The claim: "the models are tuned to align with one side of the issue, he is an article from ArsTech about it"
The reality: grok got mass-reported on X by pro-Israel accounts, leading to an automated suspension, which was undone by the X team shortly thereafter.
Absolutely nothing to do with the models aligning to one side or the other on this conflict. The claim is unfounded.
It's not that the models disagreed, the models reflected exactly the reality of the situation.
Sample output: "However, the definitive, legally binding determination of Israel’s responsibility under the Genocide Convention has not yet been made by the International Court of Justice"
The United Nations never made a ruling. You can have opinions about whether it should have, but the models are not lying to you, and at least the two examples above make very good efforts to explain the current accusations and claims made by both sides.
Stt/tts systems always seem to me so promising, but I pretty much never use voice to interface with a computer. Sometimes instead of typing on my phone, I use a voice dictation. I would be keen to use voice to control Claude code, but I've always felt that the way I speak is different from the way I write good prompts.
Fishing for anecdotes here, does anyone have any good tts/stt experiences?
If the corporate berries are really so bad, the invisible hand will push the company in the direction of society's aggregate wallet vote. Sounds like most people are fine with them. Outside of truly autocratic systems, sounds like these berries are WAI.
This reminds me of the Jewish Sabbath. Here in Tel Aviv, Saturday means no shops, much fewer restaurants, less programming on TV, gyms/etc open late/close early.
The parks and beaches are full of people just existing.
I did something similar. My computer crawls lite.cnn.com each Saturday. I feed it all into Gemini who composes a "front page" with links in HTML. Then the whole thing is converted to a PDF and uploaded to my Google drive with the day's date as the title. My Boox reader (some Chinese company) is synced to my Google Drive and I just open it from there. I didn't even code any of this, Gemini did.
It's a nice thing to read on Saturday morning with a coffee.
Yeah, I second this. Like other comments have mentioned, you'd expect a human to add a video to such a post. I wonder what urged this robot to post this to HN.
Ukraine was historically more or less a free-for-all as far as front-line cinema is concerned.
I have to imagine the situation in Iran is more difficult for a few reasons:
1. Gen AI is much better today than it was in 2022. So, both sides can generate much more realistic fakes.
2. There was an article here on HN about Iran's internet slowly coming back on a whitelist basis. We're probably getting more pro-Government videos now than we were at the beginning of the current events.
3. Further crackdown on Starlink minimizes authentic leaks (I only heard about this and have no way to confirm how impactful this really is)
I'll add my own anecdotal agreement with your suspicion though - the footage coming out of Iran has been, for me, more difficult than other conflicts to piece together into a cohesive story. Western countries are claiming 30k+ dead, and while I don't necessarily reject the claim, the situation on the ground is still very blurry to me.
Does anyone know how Iranians are _actually_ communicating right now? I remember seeing here on HN (admittedly a long time ago) some Bluetooth-mesh technologies that promised decentralized solutions to these very type of problems
Very interesting to see "Technical Analysis" in this list. I'm no expert in the field, and TA always seemed like quackery to me, but I suspect many more people believe in it than for example Cryptozoology. I personally know someone who even took a course in TA, couldn't imagine anyone taking a course in looking for Bigfoot.
If they're better - yes. ChatGPT is a very different product from Google Search. Return on Ad Spend could be significantly higher than even Google/Meta/ByteDance can offer.
As we become more and more acquainted with programming, a lot of what we do why we do it is incoherent nonsense to a beginner, but important nonetheless.
The limit is actually your time and effort. But nobody likes to write optimal assembly by hand, the balance has to be struck somewhere.
The claim: "the models are tuned to align with one side of the issue, he is an article from ArsTech about it"
The reality: grok got mass-reported on X by pro-Israel accounts, leading to an automated suspension, which was undone by the X team shortly thereafter.
Absolutely nothing to do with the models aligning to one side or the other on this conflict. The claim is unfounded.