[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"nav-categories":3,"article-openai-research-finds-that-even-its-best-models-give-wrong-answers-a-wild-proportion-of-the-time":70},{"data":4},[5,37,57,64],{"name":6,"slug":7,"categories":8},"Productivity","productivity",[9,13,17,21,25,29,33],{"id":10,"title":11,"slug":12},17,"Branding","branding",{"id":14,"title":15,"slug":16},19,"Marketing","marketing",{"id":18,"title":19,"slug":20},20,"Work","work",{"id":22,"title":23,"slug":24},34,"Community","community",{"id":26,"title":27,"slug":28},21,"For newbies","for-newbies",{"id":30,"title":31,"slug":32},24,"Investment","investment",{"id":34,"title":35,"slug":36},22,"Finance","finance",{"name":38,"slug":39,"categories":40},"Tech","tech",[41,45,49,53],{"id":42,"title":43,"slug":44},28,"Technology","technology",{"id":46,"title":47,"slug":48},32,"Artificial Intelligence","artificial-intelligence",{"id":50,"title":51,"slug":52},26,"Security and protection","security-and-protection",{"id":54,"title":55,"slug":56},31,"YouTube Blog","youtube-blog",{"name":58,"slug":59,"categories":60},"News","news",[61],{"id":62,"title":58,"slug":63},18,"quasanews",{"name":65,"slug":66,"categories":67},"Business","business",[68],{"id":69,"title":65,"slug":66},16,{"post":71,"published_news":94,"popular_news":159,"categories":230},{"title":72,"description":73,"meta_title":72,"meta_description":73,"meta_keywords":74,"text":75,"slug":76,"created_at":77,"publish_at":78,"formatted_created_at":79,"category_id":46,"links":80,"view_type":85,"video_url":86,"views":87,"likes":88,"lang":89,"comments_count":88,"category":90},"OpenAI Research Finds That Even Its Best Models Give Wrong Answers a Wild Proportion of the Time","OpenAI's latest AI models are shockingly bad at being right","","\u003Cp>Hello!\u003C/p>\n\n\u003Ch4>\u003Cstrong>BS Generator\u003C/strong>\u003C/h4>\n\n\u003Cp>\u003Ca href=\"https://quasa.io/media/openai-staff-upset-by-company-s-horrendous-new-logo\">OpenAI \u003C/a>has released a new benchmark, dubbed "SimpleQA," that's designed to measure the accuracy of the output of its own and competing artificial intelligence models.\u003C/p>\n\n\u003Cp>In doing so, the AI company has revealed just how bad its latest models are at providing correct answers. In its own tests, its cutting edge o1-preview model, which was released last month, scored an abysmal 42.7 percent success rate on the new benchmark.\u003C/p>\n\n\u003Cp>In other words, even the cream of the crop of recently announced large language models (LLMs) is far more likely to provide an outright incorrect answer than a right one — a concerning indictment, especially as the tech is starting to pervade many aspects of our everyday lives.\u003C/p>\n\n\u003Ch4>\u003Cstrong>Wrong Again\u003C/strong>\u003C/h4>\n\n\u003Cp>Competing models, like Anthropic's, scored even lower on OpenAI's SimpleQA benchmark, with its recently released \u003Ca href=\"https://quasa.io/media/claude-ai-gets-bored-during-coding-demonstration-starts-perusing-photos-of-national-parks-instead\">Claude-3.5-sonnet\u003C/a> model getting only 28.9 percent of questions right. However, the model was far more inclined to reveal its own uncertainty and decline to answer — which, given the damning results, is probably for the best.\u003C/p>\n\n\u003Cp>Worse yet, \u003Ca href=\"https://quasa.io/media/ai-safety-researcher-quits-openai-saying-its-trajectory-alarms-her\">OpenAI\u003C/a> found that its own AI models tend to vastly overestimate their own abilities, a characteristic that can lead to them being highly confident in the falsehoods they concoct.\u003C/p>\n\n\u003Cp>LLMs have long suffered from "hallucinations," an elegant term AI companies have come up with to denote their models' well-documented tendency to produce answers that are complete BS.\u003C/p>\n\n\u003Cp>Despite the very high chance of ending up with complete fabrications, the world has embraced the tech with open arms, from students generating homework assignments to developers employed by tech giants generating huge swathes of code.\u003C/p>\n\n\u003Cp>And the cracks are starting the show. Case in point, an AI model used by hospitals and built on OpenAI tech was caught this week introducing frequent hallucinations and inaccuracies while transcribing patient interactions.\u003C/p>\n\n\u003Cp>Cops across the United States are also starting to embrace AI, a terrifying development that could lead to law enforcement falsely accusing the innocent or furthering troubling biases.\u003C/p>\n\n\u003Cp>OpenAI's latest findings are yet another worrying sign that current LLMs are woefully unable to reliably tell the truth.\u003C/p>\n\n\u003Cp>It's a development that should serve as a reminder to treat any output of any LLM out there with plenty of skepticism and a willingness to go over the generated text with a fine-toothed comb.\u003C/p>\n\n\u003Cp>Whether it's a problem that can be solved with even bigger training sets — something AI leaders are rushing to assure investors of — remains an open question.\u003C/p>\n\n\u003Cp>Thank you!\u003Cbr />\nJoin us on social media!\u003Cbr />\nSee you! \u003C/p>","openai-research-finds-that-even-its-best-models-give-wrong-answers-a-wild-proportion-of-the-time","2024-11-03T16:00:49.000000Z","2024-11-04T03:00:00.000000Z","04.11.2024",{"image":81,"image_webp":82,"thumb":83,"thumb_webp":84},"https://cdn.quasa.io/images/news/Z0TGhVAbifHRnzpxql55Wt8W8NUYLBqae9EvJArK.jpg","https://cdn.quasa.io/images/news/Z0TGhVAbifHRnzpxql55Wt8W8NUYLBqae9EvJArK.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/Z0TGhVAbifHRnzpxql55Wt8W8NUYLBqae9EvJArK.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/Z0TGhVAbifHRnzpxql55Wt8W8NUYLBqae9EvJArK.webp","small",null,1588,0,"en",{"id":46,"title":47,"slug":48,"meta_title":47,"meta_description":91,"meta_keywords":91,"deleted_at":86,"created_at":92,"updated_at":93,"lang":89},"Artificial Intelligence, ai, ml, machine learning, chatgpt, future","2024-09-22T08:08:27.000000Z","2024-09-23T12:49:38.000000Z",[95,109,121,133,146],{"title":96,"description":97,"slug":98,"created_at":99,"publish_at":99,"formatted_created_at":100,"category":101,"links":102,"view_type":85,"video_url":86,"views":107,"likes":88,"lang":89,"comments_count":88,"is_pinned":108},"Cloudflare Just Made Email a First-Class Citizen for AI Agents — And Traditional Email Services Are Feeling It","On April 17, 2026, Cloudflare quietly turned a long-standing dream into reality: it moved Email Service into public beta and added full Email Sending alongside the years-old Email Routing.","cloudflare-just-made-email-a-first-class-citizen-for-ai-agents-and-traditional-email-services-are-feeling-it","2026-04-19T18:41:05.000000Z","19.04.2026",{"title":43,"slug":44},{"image":103,"image_webp":104,"thumb":105,"thumb_webp":106},"https://cdn.quasa.io/images/news/BL8rqDdPh380Xfk5TP00aXBFWdOVXI5BUQ1TuSaC.jpg","https://cdn.quasa.io/images/news/BL8rqDdPh380Xfk5TP00aXBFWdOVXI5BUQ1TuSaC.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/BL8rqDdPh380Xfk5TP00aXBFWdOVXI5BUQ1TuSaC.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/BL8rqDdPh380Xfk5TP00aXBFWdOVXI5BUQ1TuSaC.webp",7,false,{"title":110,"description":111,"slug":112,"created_at":113,"publish_at":113,"formatted_created_at":100,"category":114,"links":115,"view_type":85,"video_url":86,"views":120,"likes":88,"lang":89,"comments_count":88,"is_pinned":108},"Mozilla Nails It: Thunderbolt Brings “ChatGPT at Home” to the Enterprise — Without Vendor Lock-In","While OpenAI and Anthropic race to sell their proprietary AI platforms to big corporations, Mozilla’s subsidiary MZLA Technologies has taken a very different route.","mozilla-nails-it-thunderbolt-brings-chatgpt-at-home-to-the-enterprise-without-vendor-lock-in","2026-04-19T15:37:27.000000Z",{"title":58,"slug":63},{"image":116,"image_webp":117,"thumb":118,"thumb_webp":119},"https://cdn.quasa.io/images/news/qaAODXSpJy6qpJc0eO9DQ2Y6ccJR1tlL5i3mN0kV.jpg","https://cdn.quasa.io/images/news/qaAODXSpJy6qpJc0eO9DQ2Y6ccJR1tlL5i3mN0kV.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/qaAODXSpJy6qpJc0eO9DQ2Y6ccJR1tlL5i3mN0kV.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/qaAODXSpJy6qpJc0eO9DQ2Y6ccJR1tlL5i3mN0kV.webp",23,{"title":122,"description":123,"slug":124,"created_at":125,"publish_at":125,"formatted_created_at":100,"category":126,"links":127,"view_type":85,"video_url":86,"views":132,"likes":88,"lang":89,"comments_count":88,"is_pinned":108},"X Is Finally Cracking Down on Unlabeled Ads — And It’s Personal","For years, X (formerly Twitter) has been a playground for undisclosed promotions, coordinated spam networks, and “native” advertising that masquerades as organic content.","x-is-finally-cracking-down-on-unlabeled-ads-and-it-s-personal","2026-04-19T15:07:48.000000Z",{"title":65,"slug":66},{"image":128,"image_webp":129,"thumb":130,"thumb_webp":131},"https://cdn.quasa.io/images/news/CQJ1gdssFGyJpfhfmRU2X4WT5fk5Boc8APXsjWX6.jpg","https://cdn.quasa.io/images/news/CQJ1gdssFGyJpfhfmRU2X4WT5fk5Boc8APXsjWX6.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/CQJ1gdssFGyJpfhfmRU2X4WT5fk5Boc8APXsjWX6.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/CQJ1gdssFGyJpfhfmRU2X4WT5fk5Boc8APXsjWX6.webp",25,{"title":134,"description":135,"slug":136,"created_at":137,"publish_at":138,"formatted_created_at":100,"category":139,"links":140,"view_type":85,"video_url":86,"views":145,"likes":88,"lang":89,"comments_count":88,"is_pinned":108},"Bitcoin Developers Propose BIP-361: Quantum-Proof Migration That Would Freeze Millions of Legacy Coins","In a move that could reshape the security of Bitcoin’s unspent transaction outputs forever, Bitcoin developers have introduced BIP-361 — officially titled “Post Quantum Migration and Legacy Signature Sunset.”","bitcoin-developers-propose-bip-361-quantum-proof-migration-that-would-freeze-millions-of-legacy-coins","2026-04-17T11:38:06.000000Z","2026-04-19T11:29:00.000000Z",{"title":43,"slug":44},{"image":141,"image_webp":142,"thumb":143,"thumb_webp":144},"https://cdn.quasa.io/images/news/XW07GuAbFLRaVskP2iUsv0witLmM4GwiSlwMPZpp.jpg","https://cdn.quasa.io/images/news/XW07GuAbFLRaVskP2iUsv0witLmM4GwiSlwMPZpp.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/XW07GuAbFLRaVskP2iUsv0witLmM4GwiSlwMPZpp.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/XW07GuAbFLRaVskP2iUsv0witLmM4GwiSlwMPZpp.webp",46,{"title":147,"description":148,"slug":149,"created_at":150,"publish_at":151,"formatted_created_at":100,"category":152,"links":153,"view_type":85,"video_url":86,"views":158,"likes":88,"lang":89,"comments_count":88,"is_pinned":108},"Thomas Peterffy’s Bold Vision for Prediction Markets: Why Interactive Brokers Is Betting Big on “Useful” Bets","In a wide-ranging conversation on Bloomberg’s Odd Lots podcast, Thomas Peterffy — founder, chairman, and CEO of Interactive Brokers (IBKR) — sat down to discuss one of the most intriguing projects in his company’s 50-year history: IBKR ForecastTrader, the brokerage giant’s freshly launched prediction market platform.","thomas-peterffy-s-bold-vision-for-prediction-markets-why-interactive-brokers-is-betting-big-on-useful-bets","2026-04-16T18:39:15.000000Z","2026-04-19T09:31:00.000000Z",{"title":65,"slug":66},{"image":154,"image_webp":155,"thumb":156,"thumb_webp":157},"https://cdn.quasa.io/images/news/48nr7BL364AeGyF1lbFbh13tx14RNr0P2uUnbVe0.jpg","https://cdn.quasa.io/images/news/48nr7BL364AeGyF1lbFbh13tx14RNr0P2uUnbVe0.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/48nr7BL364AeGyF1lbFbh13tx14RNr0P2uUnbVe0.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/48nr7BL364AeGyF1lbFbh13tx14RNr0P2uUnbVe0.webp",57,[160,173,189,201,216],{"title":161,"description":162,"slug":163,"created_at":164,"publish_at":165,"formatted_created_at":166,"category":167,"links":168,"view_type":85,"video_url":86,"views":171,"likes":172,"lang":89,"comments_count":88,"is_pinned":108},"The Anatomy of an Entrepreneur","Entrepreneur is a French word that means an enterpriser. Enterprisers are people who undertake a business or enterprise with the chance of earning profits or suffering from loss.","the-anatomy-of-an-entrepreneur","2021-08-04T15:18:21.000000Z","2025-12-14T06:09:00.000000Z","14.12.2025",{"title":65,"slug":66},{"image":169,"image_webp":86,"thumb":170,"thumb_webp":170},"https://cdn.quasa.io/images/news/mVsXPTMuHZuI7UXCsENgL1Qwp1uSOf7Rz3uVPMfm.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/mVsXPTMuHZuI7UXCsENgL1Qwp1uSOf7Rz3uVPMfm.webp",70822,2,{"title":174,"description":175,"slug":176,"created_at":177,"publish_at":178,"formatted_created_at":179,"category":180,"links":181,"view_type":186,"video_url":86,"views":187,"likes":188,"lang":89,"comments_count":88,"is_pinned":108},"Advertising on QUASA","QUASA MEDIA is read by more than 400 thousand people a month. We offer to place your article, add a link or order the writing of an article for publication.","advertising-on-quasa","2022-07-06T07:33:02.000000Z","2025-12-15T17:33:02.000000Z","15.12.2025",{"title":58,"slug":63},{"image":182,"image_webp":183,"thumb":184,"thumb_webp":185},"https://cdn.quasa.io/images/news/45SvmdsTQbiyc3nxgbyHY1mpVbisYyub2BCHjqBL.jpg","https://cdn.quasa.io/images/news/45SvmdsTQbiyc3nxgbyHY1mpVbisYyub2BCHjqBL.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/45SvmdsTQbiyc3nxgbyHY1mpVbisYyub2BCHjqBL.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/45SvmdsTQbiyc3nxgbyHY1mpVbisYyub2BCHjqBL.webp","large",70586,4,{"title":190,"description":191,"slug":192,"created_at":193,"publish_at":194,"formatted_created_at":195,"category":196,"links":197,"view_type":85,"video_url":86,"views":200,"likes":188,"lang":89,"comments_count":88,"is_pinned":108},"What is a Startup?","A startup is not a new company, not a tech company, nor a new tech company. You can be a new tech company, if your goal is not to grow high and fast; then, you are not a startup. ","what-is-a-startup","2021-08-04T12:05:17.000000Z","2025-12-17T13:02:00.000000Z","17.12.2025",{"title":65,"slug":66},{"image":198,"image_webp":86,"thumb":199,"thumb_webp":199},"https://cdn.quasa.io/images/news/EOsQhSW3VXyG7a6NPdE1oZd00xfJXe3bjY5aJGb7.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/EOsQhSW3VXyG7a6NPdE1oZd00xfJXe3bjY5aJGb7.webp",68220,{"title":202,"description":203,"slug":204,"created_at":205,"publish_at":206,"formatted_created_at":207,"category":208,"links":209,"view_type":85,"video_url":86,"views":214,"likes":172,"lang":89,"comments_count":215,"is_pinned":108},"Top 5 Tips to Make More Money as a Content Creator","Content creators are one of the most desired job titles right now. Who wouldn’t want to earn a living online?","top-5-tips-to-make-more-money-as-a-content-creator","2022-01-17T17:31:51.000000Z","2026-01-17T11:30:00.000000Z","17.01.2026",{"title":19,"slug":20},{"image":210,"image_webp":211,"thumb":212,"thumb_webp":213},"https://cdn.quasa.io/images/news/gP8kiumBPpJmQv6SMieXiX1tDetx43VwFfO1P4Ca.jpg","https://cdn.quasa.io/images/news/gP8kiumBPpJmQv6SMieXiX1tDetx43VwFfO1P4Ca.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/gP8kiumBPpJmQv6SMieXiX1tDetx43VwFfO1P4Ca.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/gP8kiumBPpJmQv6SMieXiX1tDetx43VwFfO1P4Ca.webp",42197,1,{"title":217,"description":218,"slug":219,"created_at":220,"publish_at":221,"formatted_created_at":222,"category":223,"links":224,"view_type":186,"video_url":86,"views":229,"likes":172,"lang":89,"comments_count":88,"is_pinned":108},"8 Logo Design Tips for Small Businesses","Your logo tells the story of your business and the values you stand for.","8-logo-design-tips-for-small-businesses","2021-12-04T21:59:52.000000Z","2025-05-05T03:30:00.000000Z","05.05.2025",{"title":15,"slug":16},{"image":225,"image_webp":226,"thumb":227,"thumb_webp":228},"https://cdn.quasa.io/images/news/Wbx2NtS1CnTupgoQbpFMGspJ5jm4uob2hDOq33r0.jpg","https://cdn.quasa.io/images/news/Wbx2NtS1CnTupgoQbpFMGspJ5jm4uob2hDOq33r0.webp","https://cdn.quasa.io/thumbs/news-thumb/images/news/Wbx2NtS1CnTupgoQbpFMGspJ5jm4uob2hDOq33r0.jpg","https://cdn.quasa.io/thumbs/news-thumb/images/news/Wbx2NtS1CnTupgoQbpFMGspJ5jm4uob2hDOq33r0.webp",41293,[231,232,233,234,235,236,237,238,239,240,241,242,243],{"title":23,"slug":24},{"title":47,"slug":48},{"title":55,"slug":56},{"title":43,"slug":44},{"title":51,"slug":52},{"title":31,"slug":32},{"title":35,"slug":36},{"title":27,"slug":28},{"title":19,"slug":20},{"title":15,"slug":16},{"title":58,"slug":63},{"title":11,"slug":12},{"title":65,"slug":66}]