#Tag
The BBC, NRK and 20 other public broadcasters allowed AI assistants to scrape their websites. They were then tested on their ability to answer questions about news content.
Today they jointly published the research and issued a warning around the use of AI assistants to answer questions about news, citing factual errors and the misrepresentation of source material affecting AI assistants.
🇳🇴 https://nrkbeta.no/2025/10/22/ki-assistenter-testet-halvparten-av-svarene-inneholdt-feil/
I don't get the point of introducing erotica to ai models, especially from a company whose motto is for AI to benefit all of humanity.
Burning runaway to train models to make people confide in something that only feeds the user with delusions rather than addressing real world issues is beyond dystopian.
Might as well support your local OF model rather than this.
I think there’s a real possibility that local, running on consumer electronic devices, generative AI without the need for expensive processors, data centers, massive amounts of water and electricity may well be the actual long term way forward for generative AIs like LLM, image and video generators.
@neil This is going to be the tip of a pin stuck in an iceberg.
I'm frankly amazed at how long it is taking for criminals to weaponise #LLMs like this. Even my spam email is still trivial to spot.
As with cybersecurity, regulation is non-existent and governments don't care or are made up of people who only know what lobbyists bother to tell them.
I despair...
...and keep working on #AutonomiDweb
In reference to #LLMs, I want to really underscore the difference in speaking and writing.
What is so astonishing about the speaking human is that by the time we are speaking fluently, we have adopted and incorporated a large amount of the cultural rules, norms and prejudices that piggyback on any given language. So when we open our mouths and speak, it comes out fast, often fairly unprocessed, and full of that baggage.
In reference to #LLMs, I want to really underscore the difference in speaking and writing.
What is so astonishing about the speaking human is that by the time we are speaking fluently, we have adopted and incorporated a large amount of the cultural rules, norms and prejudices that piggyback on any given language. So when we open our mouths and speak, it comes out fast, often fairly unprocessed, and full of that baggage.
In reference to #LLMs, I want to really underscore the difference in speaking and writing.
What is so astonishing about the speaking human is that by the time we are speaking fluently, we have adopted and incorporated a large amount of the cultural rules, norms and prejudices that piggyback on any given language. So when we open our mouths and speak, it comes out fast, often fairly unprocessed, and full of that baggage.
Who governs the values within AI and how they are managed is an issue of profound importance for liberal democracy. https://www.japantimes.co.jp/commentary/2025/10/01/world/trump-and-the-tech-giants/?utm_medium=Social&utm_source=mastodon #commentary #worldnews #donaldtrump #sundarpichai #jeffbezos #markzuckerberg #elonmusk #meta #facebook #google #amazon #apple #chatgpt #joebiden #freespeech #ai #llms
"the #AI bubble is driven by monopolists who've conquered their markets and have no more growth potential, who are desperate to convince investors that they can continue to grow by moving into some other sector...
when the bubble bursts, the money-hemorrhaging "foundation models" will be shut off and we'll lose the AI that can't do your job, and you will be long gone" — @pluralistic
https://pluralistic.net/2025/09/27/econopocalypse/#subprime-intelligence
"the #AI bubble is driven by monopolists who've conquered their markets and have no more growth potential, who are desperate to convince investors that they can continue to grow by moving into some other sector...
when the bubble bursts, the money-hemorrhaging "foundation models" will be shut off and we'll lose the AI that can't do your job, and you will be long gone" — @pluralistic
https://pluralistic.net/2025/09/27/econopocalypse/#subprime-intelligence
...it has no wants, period. All it can do is transform a prompt into something that seems like the kind of thing that would follow from that prompt. It's a next-word-guessing machine."
-- @pluralistic
https://pluralistic.net/2025/09/17/automating-gang-stalking-delusion/
2/2
#AI = #LLMs = #NextWordGuessingMachines
#enshittification
#hyperenshittification
...it has no wants, period. All it can do is transform a prompt into something that seems like the kind of thing that would follow from that prompt. It's a next-word-guessing machine."
-- @pluralistic
https://pluralistic.net/2025/09/17/automating-gang-stalking-delusion/
2/2
#AI = #LLMs = #NextWordGuessingMachines
#enshittification
#hyperenshittification
The search engine @ecosia have a survey running. They want to know how you use their search engine and how you use AI.
You can tell them what you think about both of those things here: https://feedback.surveylab.com/38a/5f0d0476/
🙃
New Report From #NewsGuard: #AI False Information Rate Nearly Doubles in One Year https://www.newsguardtech.com/ai-monitor/august-2025-ai-false-claim-monitor/#LLMs#GPT
New Report From #NewsGuard: #AI False Information Rate Nearly Doubles in One Year https://www.newsguardtech.com/ai-monitor/august-2025-ai-false-claim-monitor/#LLMs#GPT
A space for Bonfire maintainers and contributors to communicate
