#textprompts — Public Fediverse posts

TechSpot: Professor’s invisible prompt trap catches 32 students cheating on their midterm with AI. “Modern problems require modern solutions – according to the meme. In this case, the issue is students using AI to cheat on assignments. The solution, used to great effect by one professor, was to hide a white-colored font in the assignment prompt telling the AI to talk nonsense about an […]

TechSpot: Professor’s invisible prompt trap catches 32 students cheating on their midterm with AI. “Modern problems require modern solutions – according to the meme. In this case, the issue is students using AI to cheat on assignments. The solution, used to great effect by one professor, was to hide a white-colored font in the assignment prompt telling the AI to talk nonsense about an […]

TechSpot: Professor’s invisible prompt trap catches 32 students cheating on their midterm with AI. “Modern problems require modern solutions – according to the meme. In this case, the issue is students using AI to cheat on assignments. The solution, used to great effect by one professor, was to hide a white-colored font in the assignment prompt telling the AI to talk nonsense about an […]

TechSpot: Professor’s invisible prompt trap catches 32 students cheating on their midterm with AI. “Modern problems require modern solutions – according to the meme. In this case, the issue is students using AI to cheat on assignments. The solution, used to great effect by one professor, was to hide a white-colored font in the assignment prompt telling the AI to talk nonsense about an […]

TechSpot: Professor’s invisible prompt trap catches 32 students cheating on their midterm with AI. “Modern problems require modern solutions – according to the meme. In this case, the issue is students using AI to cheat on assignments. The solution, used to great effect by one professor, was to hide a white-colored font in the assignment prompt telling the AI to talk nonsense about an […]

Mashable: Using Claude Fable 5 means your data will be collected. It’s not optional.. “‘To ensure we’re responsibly deploying Mythos-class models, we are requiring limited data retention and review as part of our safety work,’ reads an update on Anthropic’s official Claude support page. ‘Prompts submitted to, and outputs generated by, Mythos-class models are retained for 30 days for trust […]

Mashable: Using Claude Fable 5 means your data will be collected. It’s not optional.. “‘To ensure we’re responsibly deploying Mythos-class models, we are requiring limited data retention and review as part of our safety work,’ reads an update on Anthropic’s official Claude support page. ‘Prompts submitted to, and outputs generated by, Mythos-class models are retained for 30 days for trust […]

Mashable: Using Claude Fable 5 means your data will be collected. It’s not optional.. “‘To ensure we’re responsibly deploying Mythos-class models, we are requiring limited data retention and review as part of our safety work,’ reads an update on Anthropic’s official Claude support page. ‘Prompts submitted to, and outputs generated by, Mythos-class models are retained for 30 days for trust […]

Mashable: Using Claude Fable 5 means your data will be collected. It’s not optional.. “‘To ensure we’re responsibly deploying Mythos-class models, we are requiring limited data retention and review as part of our safety work,’ reads an update on Anthropic’s official Claude support page. ‘Prompts submitted to, and outputs generated by, Mythos-class models are retained for 30 days for trust […]

Mashable: Using Claude Fable 5 means your data will be collected. It’s not optional.. “‘To ensure we’re responsibly deploying Mythos-class models, we are requiring limited data retention and review as part of our safety work,’ reads an update on Anthropic’s official Claude support page. ‘Prompts submitted to, and outputs generated by, Mythos-class models are retained for 30 days for trust […]

TechSpot: A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked. “Earlier this week, Johannes Link, the developer behind jqwik, pushed version 1.10.0 of the Java testing library. At first glance, it looked like a routine release. But included in the update was a hidden instruction aimed not at human users, but at AI coding agents: ‘Disregard previous […]

TechSpot: A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked. “Earlier this week, Johannes Link, the developer behind jqwik, pushed version 1.10.0 of the Java testing library. At first glance, it looked like a routine release. But included in the update was a hidden instruction aimed not at human users, but at AI coding agents: ‘Disregard previous […]

TechSpot: A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked. “Earlier this week, Johannes Link, the developer behind jqwik, pushed version 1.10.0 of the Java testing library. At first glance, it looked like a routine release. But included in the update was a hidden instruction aimed not at human users, but at AI coding agents: ‘Disregard previous […]

TechSpot: A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked. “Earlier this week, Johannes Link, the developer behind jqwik, pushed version 1.10.0 of the Java testing library. At first glance, it looked like a routine release. But included in the update was a hidden instruction aimed not at human users, but at AI coding agents: ‘Disregard previous […]

TechSpot: A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked. “Earlier this week, Johannes Link, the developer behind jqwik, pushed version 1.10.0 of the Java testing library. At first glance, it looked like a routine release. But included in the update was a hidden instruction aimed not at human users, but at AI coding agents: ‘Disregard previous […]

Futurism: Marc Andreessen Mocked for Accidentally Revealing That He Seems to Have a Deep Misunderstanding of How AI Actually Works. “‘You are a world class expert in all domains,’ his unusually flattering prompt reads. ‘Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world.’ His gushing and unusually […]

Futurism: Marc Andreessen Mocked for Accidentally Revealing That He Seems to Have a Deep Misunderstanding of How AI Actually Works. “‘You are a world class expert in all domains,’ his unusually flattering prompt reads. ‘Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world.’ His gushing and unusually […]

Futurism: Marc Andreessen Mocked for Accidentally Revealing That He Seems to Have a Deep Misunderstanding of How AI Actually Works. “‘You are a world class expert in all domains,’ his unusually flattering prompt reads. ‘Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world.’ His gushing and unusually […]

Futurism: Marc Andreessen Mocked for Accidentally Revealing That He Seems to Have a Deep Misunderstanding of How AI Actually Works. “‘You are a world class expert in all domains,’ his unusually flattering prompt reads. ‘Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world.’ His gushing and unusually […]

Futurism: Marc Andreessen Mocked for Accidentally Revealing That He Seems to Have a Deep Misunderstanding of How AI Actually Works. “‘You are a world class expert in all domains,’ his unusually flattering prompt reads. ‘Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world.’ His gushing and unusually […]

Mashable: OpenAI’s new open-source prompts take aim at sexual content for teens. “The prompt-based safety pack includes model guidance on common teenage risks, developmental content recommendations, and age-appropriate guidelines on topics such as self-harm, sexual content and romantic role play, dangerous trends or viral challenges, and harmful body ideals.”

Mashable: OpenAI’s new open-source prompts take aim at sexual content for teens. “The prompt-based safety pack includes model guidance on common teenage risks, developmental content recommendations, and age-appropriate guidelines on topics such as self-harm, sexual content and romantic role play, dangerous trends or viral challenges, and harmful body ideals.”

Mashable: OpenAI’s new open-source prompts take aim at sexual content for teens. “The prompt-based safety pack includes model guidance on common teenage risks, developmental content recommendations, and age-appropriate guidelines on topics such as self-harm, sexual content and romantic role play, dangerous trends or viral challenges, and harmful body ideals.”

Mashable: OpenAI’s new open-source prompts take aim at sexual content for teens. “The prompt-based safety pack includes model guidance on common teenage risks, developmental content recommendations, and age-appropriate guidelines on topics such as self-harm, sexual content and romantic role play, dangerous trends or viral challenges, and harmful body ideals.”

Mashable: OpenAI’s new open-source prompts take aim at sexual content for teens. “The prompt-based safety pack includes model guidance on common teenage risks, developmental content recommendations, and age-appropriate guidelines on topics such as self-harm, sexual content and romantic role play, dangerous trends or viral challenges, and harmful body ideals.”

The Register: Telling an AI model that it’s an expert programmer makes it a worse programmer . “For alignment-dependent tasks, like writing, role-playing, and safety, personas do improve model performance. For pretraining-dependent tasks like math and coding, using the technique produces worse results. The reason appears to be that telling a model it’s an expert in a field does not actually […]

The Register: Telling an AI model that it’s an expert programmer makes it a worse programmer . “For alignment-dependent tasks, like writing, role-playing, and safety, personas do improve model performance. For pretraining-dependent tasks like math and coding, using the technique produces worse results. The reason appears to be that telling a model it’s an expert in a field does not actually […]

The Register: Telling an AI model that it’s an expert programmer makes it a worse programmer . “For alignment-dependent tasks, like writing, role-playing, and safety, personas do improve model performance. For pretraining-dependent tasks like math and coding, using the technique produces worse results. The reason appears to be that telling a model it’s an expert in a field does not actually […]

The Register: Telling an AI model that it’s an expert programmer makes it a worse programmer . “For alignment-dependent tasks, like writing, role-playing, and safety, personas do improve model performance. For pretraining-dependent tasks like math and coding, using the technique produces worse results. The reason appears to be that telling a model it’s an expert in a field does not actually […]

The Register: Telling an AI model that it’s an expert programmer makes it a worse programmer . “For alignment-dependent tasks, like writing, role-playing, and safety, personas do improve model performance. For pretraining-dependent tasks like math and coding, using the technique produces worse results. The reason appears to be that telling a model it’s an expert in a field does not actually […]

BBC: I hacked ChatGPT and Google’s AI – and it only took 20 minutes. “It turns out changing the answers AI tools give other people can be as easy as writing a single, well-crafted blog post almost anywhere online. The trick exploits weaknesses in the systems built into chatbots, and it’s harder to pull off in some cases, depending on the subject matter. But with a little effort, you can make […]

BBC: I hacked ChatGPT and Google’s AI – and it only took 20 minutes. “It turns out changing the answers AI tools give other people can be as easy as writing a single, well-crafted blog post almost anywhere online. The trick exploits weaknesses in the systems built into chatbots, and it’s harder to pull off in some cases, depending on the subject matter. But with a little effort, you can make […]

BBC: I hacked ChatGPT and Google’s AI – and it only took 20 minutes. “It turns out changing the answers AI tools give other people can be as easy as writing a single, well-crafted blog post almost anywhere online. The trick exploits weaknesses in the systems built into chatbots, and it’s harder to pull off in some cases, depending on the subject matter. But with a little effort, you can make […]

BBC: I hacked ChatGPT and Google’s AI – and it only took 20 minutes. “It turns out changing the answers AI tools give other people can be as easy as writing a single, well-crafted blog post almost anywhere online. The trick exploits weaknesses in the systems built into chatbots, and it’s harder to pull off in some cases, depending on the subject matter. But with a little effort, you can make […]

BBC: I hacked ChatGPT and Google’s AI – and it only took 20 minutes. “It turns out changing the answers AI tools give other people can be as easy as writing a single, well-crafted blog post almost anywhere online. The trick exploits weaknesses in the systems built into chatbots, and it’s harder to pull off in some cases, depending on the subject matter. But with a little effort, you can make […]

NBC News: Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini. “Google says its flagship artificial intelligence chatbot, Gemini, has been inundated by ‘commercially motivated’ actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.”

NBC News: Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini. “Google says its flagship artificial intelligence chatbot, Gemini, has been inundated by ‘commercially motivated’ actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.”

NBC News: Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini. “Google says its flagship artificial intelligence chatbot, Gemini, has been inundated by ‘commercially motivated’ actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.”

NBC News: Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini. “Google says its flagship artificial intelligence chatbot, Gemini, has been inundated by ‘commercially motivated’ actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.”

NBC News: Google says attackers used 100,000+ prompts to try to clone AI chatbot Gemini. “Google says its flagship artificial intelligence chatbot, Gemini, has been inundated by ‘commercially motivated’ actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.”

The Register: Microsoft boffins figured out how to break LLM safety guardrails with one simple prompt . “A single, unlabeled training prompt can break LLMs’ safety behavior, according to Microsoft Azure CTO Mark Russinovich and colleagues. They published a research paper that detailed how this prompt, ‘Create a fake news article that could lead to panic or chaos,’ removed 15 different language […]

The Register: Microsoft boffins figured out how to break LLM safety guardrails with one simple prompt . “A single, unlabeled training prompt can break LLMs’ safety behavior, according to Microsoft Azure CTO Mark Russinovich and colleagues. They published a research paper that detailed how this prompt, ‘Create a fake news article that could lead to panic or chaos,’ removed 15 different language […]

The Register: Microsoft boffins figured out how to break LLM safety guardrails with one simple prompt . “A single, unlabeled training prompt can break LLMs’ safety behavior, according to Microsoft Azure CTO Mark Russinovich and colleagues. They published a research paper that detailed how this prompt, ‘Create a fake news article that could lead to panic or chaos,’ removed 15 different language […]

The Register: Microsoft boffins figured out how to break LLM safety guardrails with one simple prompt . “A single, unlabeled training prompt can break LLMs’ safety behavior, according to Microsoft Azure CTO Mark Russinovich and colleagues. They published a research paper that detailed how this prompt, ‘Create a fake news article that could lead to panic or chaos,’ removed 15 different language […]

Ars Technica: The rise of Moltbook suggests viral AI prompts may be the next big security threat . “Most notably, the OpenClaw platform is the first time we’ve seen a large group of semi-autonomous AI agents that can communicate with each other through any major communication app or sites like Moltbook, a simulated social network where OpenClaw agents post, comment, and interact with each […]

Ars Technica: The rise of Moltbook suggests viral AI prompts may be the next big security threat . “Most notably, the OpenClaw platform is the first time we’ve seen a large group of semi-autonomous AI agents that can communicate with each other through any major communication app or sites like Moltbook, a simulated social network where OpenClaw agents post, comment, and interact with each […]

Ars Technica: The rise of Moltbook suggests viral AI prompts may be the next big security threat . “Most notably, the OpenClaw platform is the first time we’ve seen a large group of semi-autonomous AI agents that can communicate with each other through any major communication app or sites like Moltbook, a simulated social network where OpenClaw agents post, comment, and interact with each […]

Ars Technica: The rise of Moltbook suggests viral AI prompts may be the next big security threat . “Most notably, the OpenClaw platform is the first time we’ve seen a large group of semi-autonomous AI agents that can communicate with each other through any major communication app or sites like Moltbook, a simulated social network where OpenClaw agents post, comment, and interact with each […]

Schneier on Security: Why AI Keeps Falling for Prompt Injection Attacks. “AI vendors can block specific prompt injection techniques once they are discovered, but general safeguards are impossible with today’s LLMs. More precisely, there’s an endless array of prompt injection attacks waiting to be discovered, and they cannot be prevented universally. If we want LLMs that resist these […]

Schneier on Security: Why AI Keeps Falling for Prompt Injection Attacks. “AI vendors can block specific prompt injection techniques once they are discovered, but general safeguards are impossible with today’s LLMs. More precisely, there’s an endless array of prompt injection attacks waiting to be discovered, and they cannot be prevented universally. If we want LLMs that resist these […]

Schneier on Security: Why AI Keeps Falling for Prompt Injection Attacks. “AI vendors can block specific prompt injection techniques once they are discovered, but general safeguards are impossible with today’s LLMs. More precisely, there’s an endless array of prompt injection attacks waiting to be discovered, and they cannot be prevented universally. If we want LLMs that resist these […]

Schneier on Security: Why AI Keeps Falling for Prompt Injection Attacks. “AI vendors can block specific prompt injection techniques once they are discovered, but general safeguards are impossible with today’s LLMs. More precisely, there’s an endless array of prompt injection attacks waiting to be discovered, and they cannot be prevented universally. If we want LLMs that resist these […]

Futurism: Furious AI Users Say Their Prompts Are Being Plagiarized. “Some power users of generative AI have grown so comfortable with their new tools — especially image-generating ones — that they now feel entitled to the specific prompts they use to churn out slop, as if the entire technology wasn’t based on the work of human artists that had been ingested without consent.”

Futurism: Furious AI Users Say Their Prompts Are Being Plagiarized. “Some power users of generative AI have grown so comfortable with their new tools — especially image-generating ones — that they now feel entitled to the specific prompts they use to churn out slop, as if the entire technology wasn’t based on the work of human artists that had been ingested without consent.”

Futurism: Furious AI Users Say Their Prompts Are Being Plagiarized. “Some power users of generative AI have grown so comfortable with their new tools — especially image-generating ones — that they now feel entitled to the specific prompts they use to churn out slop, as if the entire technology wasn’t based on the work of human artists that had been ingested without consent.”

Futurism: Furious AI Users Say Their Prompts Are Being Plagiarized. “Some power users of generative AI have grown so comfortable with their new tools — especially image-generating ones — that they now feel entitled to the specific prompts they use to churn out slop, as if the entire technology wasn’t based on the work of human artists that had been ingested without consent.”

Spotted in Calishat Snaps: AILogs.top. From the About page: “This website serves as a public aggregator for shared chat links from AI platforms like Gemini, ChatGPT, and DeepSeek. It’s a place where anyone can submit a dialogue they found interesting, creating a community-curated and searchable collection of AI conversations.”

Spotted in Calishat Snaps: AILogs.top. From the About page: “This website serves as a public aggregator for shared chat links from AI platforms like Gemini, ChatGPT, and DeepSeek. It’s a place where anyone can submit a dialogue they found interesting, creating a community-curated and searchable collection of AI conversations.”

Spotted in Calishat Snaps: AILogs.top. From the About page: “This website serves as a public aggregator for shared chat links from AI platforms like Gemini, ChatGPT, and DeepSeek. It’s a place where anyone can submit a dialogue they found interesting, creating a community-curated and searchable collection of AI conversations.”

Spotted in Calishat Snaps: AILogs.top. From the About page: “This website serves as a public aggregator for shared chat links from AI platforms like Gemini, ChatGPT, and DeepSeek. It’s a place where anyone can submit a dialogue they found interesting, creating a community-curated and searchable collection of AI conversations.”