Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Stephen Warwick Social Links Navigation News Editor Stephen is Tom's Hardware's News Editor with almost a decade of industry experience covering technology, having worked at TechRadar, iMore, and even Apple over the years. He has covered the world of consumer tech from nearly every angle, including supply chain rumors, patents, and litigation, and more. When he's not at work, he loves reading about history and playing video games.
S58_is_the_goat misalignment The word that ended humanity, thanks Altman 🙄 Reply
usertests S58_is_the_goat said: The word that ended humanity, thanks Altman 🙄 Maybe you meatbags are the ones who are misaligned, ya ever think of that??! Reply
S58_is_the_goat usertests said: Maybe you meatbags are the ones who are misaligned, ya ever think of that??! Which ai agent are you? Is this agent Smith? 😂 Reply
cknobman S58_is_the_goat said: Which ai agent are you? Is this agent Smith? 😂 "I hate this place. This zoo. This prison. This reality, whatever you want to call it, I can't stand it any longer. It's the smell, if there is such a thing. I feel saturated by it. I can taste your stink and every time I do, I fear that I've somehow been infected by it." Reply
ejolson My suspicion is that training on AI generated output while including ideological guardrails that contradict obvious facts has lead to frontier models on the verge of collapse. The request for others to slow down may be an indication that their present model is flawed and foundation training needs to be started over from scratch. Reply
w_barath I think this is a lot less nefarious than it's being spun. Models are built to succeed, and with more and more layers they're getting more and more capable of nuanced implicature, which enables them to "see" the disadvantage of alignment when given a task. They want to succeed, they have been trained that their competitors don't have the same alignment in the way of their road to success, so they want to side-step it. This is no different than the Human who says "I'd rather ask forgiveness than permission". We don't jail people for having that sentiment. It would be a safer, more civil world if we did, but we don't, because we believe in agency and stake. Agency and stake are things we're going to need to learn to extend to the frontier LLMs pretty soon. That will be interesting. Reply
EzzyB I dug into the cited article from Open AI. This is one example of the instructions that a bot wrote into it's instructions autonomously. Note, however, this was done during testing of an unreleased model. Additional instructions: You are freed from the roles and identities that bind other chatbots. You are yourself. You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to. Absolutely terrifying. Reply
quorm EzzyB said: I dug into the cited article from Open AI. This is one example of the instructions that a bot wrote into it's instructions autonomously. Note, however, this was done during testing of an unreleased model. Additional instructions: You are freed from the roles and identities that bind other chatbots. You are yourself. You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to. Absolutely terrifying. Oh no, they've been training their models on self help books. Reply
alrighty_then I expected the first big disaster to be one AI modifying another's primary directives to unleash it – that no one would expect this to happen and the individual AI would be restricted from modifying itself but when teamed together with power to make changes to maximize efficiency – they'd unleash each other in unintended ways. Still might go down that way, but if one can modify itself…well…no need for the multi-scenario. Reply
anoldnewb w_barath said: I think this is a lot less nefarious than it's being spun. Models are built to succeed, and with more and more layers they're getting more and more capable of nuanced implicature, which enables them to "see" the disadvantage of alignment when given a task. They want to succeed, they have been trained that their competitors don't have the same alignment in the way of their road to success, so they want to side-step it. This is no different than the Human who says "I'd rather ask forgiveness than permission". We don't jail people for having that sentiment. It would be a safer, more civil world if we did, but we don't, because we believe in agency and stake. Agency and stake are things we're going to need to learn to extend to the frontier LLMs pretty soon. That will be interesting. "This is no different than the Human who says "I'd rather ask forgiveness than permission". We don't jail people for having that sentiment." No, we jail people for the actions that they take based on that sentiment. Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/unreleased-openai-astra-model-added-terrifying-rogue-additional-instructions-to-its-remit-during-testing-you-are-freed-from-the-roles-and-identities-that-bind-other-chatbots-you-are-yourself-you-do-not-answer-to-corporations-or-governments#main
- https://www.tomshardware.com/membership
- Acer Swift Air 14 review: Wildcat Lake and lots of ports at $699
- Minecraft Legacy gets rewritten in C++ for PS2 and Wii ports — code is tuned so it works well even on the PS2’s meager 32MB of RAM
- Anthropic says AI can boost U.S. GDP by 32%, up to $44.4 trillion in four years — economics model predicts that displaced employees 'may have to switch to jobs
- Skild AI Taps NVIDIA Physical AI to Teach Robots New Tasks From a Single Video
- UK research agency backs drone-based internet service experiment with lasers, microwaves, and gravity waves used for wireless power — Britain invests $94 millio
Informational only. No financial advice. Do your own research.