Linking pages
- New Meta AI demo writes racist and inaccurate scientific literature, gets pulled | Ars Technica https://arstechnica.com/information-technology/2022/11/after-controversy-meta-pulls-demo-of-ai-model-that-writes-scientific-papers/ 313 comments
- AI-powered Bing Chat spills its secrets via prompt injection attack [Updated] | Ars Technica https://arstechnica.com/information-technology/2023/02/ai-powered-bing-chat-spills-its-secrets-via-prompt-injection-attack/ 222 comments
- Meta researchers create AI that masters Diplomacy, tricking human players | Ars Technica https://arstechnica.com/information-technology/2022/11/meta-researchers-create-ai-that-masters-diplomacy-tricking-human-players/ 189 comments
- Dead grandma locket request tricks Bing Chat’s AI into solving security puzzle | Ars Technica https://arstechnica.com/information-technology/2023/10/sob-story-about-dead-grandma-tricks-microsoft-ai-into-solving-captcha/ 179 comments
- ASCII art elicits harmful responses from 5 major AI chatbots | Ars Technica https://arstechnica.com/security/2024/03/researchers-use-ascii-art-to-elicit-harmful-responses-from-5-major-ai-chatbots/ 134 comments
- Soon, the tech behind ChatGPT may help drone operators decide which enemies to kill - Ars Technica https://arstechnica.com/ai/2024/12/openai-and-anduril-team-up-to-build-ai-powered-drone-defense-systems/ 95 comments
- White House challenges hackers to break top AI models at DEF CON 31 | Ars Technica https://arstechnica.com/information-technology/2023/05/white-house-challenges-hackers-to-break-top-ai-models-at-def-con-31/ 80 comments
- Uber was breached to its core, purportedly by an 18-year-old. Here’s what’s known | Ars Technica https://arstechnica.com/information-technology/2022/09/uber-was-hacked-to-its-core-purportedly-by-an-18-year-old-here-are-the-basics/ 72 comments
- Hungry for AI? New supercomputer contains 16 dinner-plate-size chips | Ars Technica https://arstechnica.com/information-technology/2022/11/hungry-for-ai-new-supercomputer-contains-16-dinner-plate-size-chips/ 68 comments
- Herzog and Žižek become uncanny AI bots trapped in endless conversation | Ars Technica https://arstechnica.com/information-technology/2022/11/herzog-and-zizek-become-uncanny-ai-bots-trapped-in-endless-conversation/ 66 comments
- AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic | Ars Technica https://arstechnica.com/information-technology/2024/01/ai-poisoning-could-turn-open-models-into-destructive-sleeper-agents-says-anthropic/ 65 comments
- Ban warnings fly as users dare to probe the “thoughts” of OpenAI’s latest model | Ars Technica https://arstechnica.com/information-technology/2024/09/openai-threatens-bans-for-probing-new-ai-models-reasoning-process/ 28 comments
- Meet Ghostwriter, a haunted AI-powered typewriter that talks to you | Ars Technica https://arstechnica.com/information-technology/2022/12/meet-ghostwriter-a-haunted-ai-powered-typewriter-that-talks-to-you/ 19 comments
- Cheap AI “video scraping” can now extract data from any screen recording https://arstechnica.com/ai/2024/10/cheap-ai-video-scraping-can-now-extract-data-from-any-screen-recording/ 16 comments
- We interviewed Linux OS through an AI bot to discover its secrets | Ars Technica https://arstechnica.com/information-technology/2022/09/we-interviewed-linux-os-through-an-ai-bot-to-discover-its-secrets/ 15 comments
- Thanks to AI, the future of programming may involve YELLING IN ALL CAPS | Ars Technica https://arstechnica.com/information-technology/2023/10/thanks-to-ai-the-future-of-programming-may-involve-yelling-in-all-caps/ 10 comments
- Nvidia and Microsoft team up to build massive AI cloud computer | Ars Technica https://arstechnica.com/information-technology/2022/11/nvidia-and-microsoft-team-up-to-build-massive-ai-cloud-computer/ 8 comments
- OpenAI upgrades GPT-3, stunning with rhyming poetry and lyrics | Ars Technica https://arstechnica.com/information-technology/2022/11/openai-conquers-rhyming-poetry-with-new-gpt-3-update/ 7 comments
- OpenAI invites everyone to test new AI-powered chatbot—with amusing results | Ars Technica https://arstechnica.com/information-technology/2022/12/openai-invites-everyone-to-test-new-ai-powered-chatbot-with-amusing-results/ 3 comments
- You can now run a GPT-3 level AI model on your laptop, phone, and Raspberry Pi | Ars Technica https://arstechnica.com/information-technology/2023/03/you-can-now-run-a-gpt-3-level-ai-model-on-your-laptop-phone-and-raspberry-pi/ 2 comments
Linked pages
- Prompt injection attacks against GPT-3 https://simonwillison.net/2022/Sep/12/prompt-injection/ 119 comments
- Uber was breached to its core, purportedly by an 18-year-old. Here’s what’s known | Ars Technica https://arstechnica.com/information-technology/2022/09/uber-was-hacked-to-its-core-purportedly-by-an-18-year-old-here-are-the-basics/ 72 comments
- How security flaws work: SQL injection | Ars Technica http://arstechnica.com/information-technology/2016/10/how-security-flaws-work-sql-injection/ 46 comments
- Riley Goodside on Twitter: "Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. https://t.co/I0NVr9LOJq" / Twitter https://twitter.com/goodside/status/1569128808308957185 15 comments
- GPT-3 Powers the Next Generation of Apps https://openai.com/blog/gpt-3-apps/ 1 comment
- [2209.02128] Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples https://arxiv.org/abs/2209.02128 0 comments
- leastfavorite! ⟦stream subject⟧ on Twitter: "wow guys, i was skeptical at first but it really seems like AI is the future https://t.co/2Or6RVc5of" / Twitter https://twitter.com/leastfavorite_/status/1570475633557348355 0 comments
- I don’t know how to solve prompt injection https://simonwillison.net/2022/Sep/16/prompt-injection-solutions/ 0 comments
- The end of Ethereum mining could be a bonanza for GPU shoppers | Ars Technica https://arstechnica.com/gaming/2022/09/the-end-of-ethereum-mining-could-be-a-bonanza-for-gpu-shoppers/ 0 comments
Related searches:
Search whole site: site:arstechnica.com
Search title: Twitter pranksters derail GPT-3 bot with newly discovered “prompt injection” hack | Ars Technica
See how to search.