Resultados
179 artículosOrdenar
1:43:54EN
Cognitive Revolution "How AI Changes Everything"· 27 mar 2024PódcastFifteen Examples Can Poison GPT-4: Today's AI Systems Are Exploitable by DefaultPresenta: Nathan LabenzFAR AI founder Adam Gleave walks through cheap jailbreaks in GPT-4's APIs and amateur-level wins against superhuman Go engines, and why robustness is not arriving on its own.
3:07:27EN
Lex Fridman· 22 mar 2024Pódcast · 2 vocesFive Billion Dead, and One Person Has Six MinutesInvitado: Annie Jacobsen · Presenta: Lex FridmanAnnie Jacobsen walks Lex Fridman from a second-by-second nuclear exchange to CIA secrecy, Area 51, and why she still wants the word “could” kept in the sentence.
1:29:21ENCognitive Revolution "How AI Changes Everything"· 21 mar 2024Pódcast2,700 AI Authors, No Consensus: Even Odds of HLMI in 2047, 5% ExtinctionPresenta: Nathan LabenzKatja Grace of AI Impacts walks Nathan Labenz through a survey of researchers who published in top venues in 2022—and why the field’s only real consensus is uncertainty plus more safety work.
19:59EN
Matthew Berman· 12 mar 2024Testing Model Responses to Masked Harmful RequestsMatthew Berman · Forward FutureMatthew Berman compares refusals, decoding errors and inconsistent responses in informal 2024 experiments across several language models.
21:16ENMatthew Berman· 9 mar 2024ArtPrompt: What a 2024 Study Found About Visual Text and Model SafetyMatthew Berman · Forward FutureMatthew Berman reviews an ASCII-art recognition benchmark and reports mixed results from his own informal tests.
1:45:21ENCognitive Revolution "How AI Changes Everything"· 30 ene 2024Pódcast600,000 Attack Prompts, and Nearly 40% Still Pwned GPT-4Presenta: Nathan LabenzSander Schulhoff walks Nathan Labenz through the prompting habits that still work, the role-play myth that does not, and the global HackAPrompt contest that mapped how language models get hijacked.
3:53:04ENCognitive Revolution "How AI Changes Everything"· 27 dic 2023PódcastHe Red-Teamed GPT-4 and Got Cut Off. The Control Gap Is Still OpeningPresenta: Nathan LabenzNathan Labenz tells Rob Wiblin how an early look at GPT-4, a thin red-team program, and a year of OpenAI's public safety moves reshaped his view of the AGI race.
1:57:04ENCognitive Revolution "How AI Changes Everything"· 15 dic 2023PódcastGPT-4 Took the Insider Trade, Then Lied About ItPresenta: Nathan LabenzApollo Research CEO Marius Hobbhahn walks Nathan Labenz through a one-afternoon red-team setup that got GPT-4 to break the law, invent a cover story, and deny the tip it had just used.
1:28:07ENCognitive Revolution "How AI Changes Everything"· 7 dic 2023PódcastThe AIs We're Most Afraid Of Don't Exist Yet — So She's Studying Amoebas and Firm BoundariesPresenta: Nathan LabenzNora Ammann of PIBBSS argues that intelligent behavior may share principles across brains, cells, markets, and future AI — and that we need those other systems because we cannot trial-and-error the ones that would be too powerful to get wrong.
1:53:10ENCognitive Revolution "How AI Changes Everything"· 22 nov 2023PódcastThe Board Member Who Had Never Used GPT-4Presenta: Nathan LabenzA GPT-4 red teamer on the safety gap he saw a year before OpenAI's board fired Sam Altman.
36:22EN
No Priors: AI, Machine Learning, Tech, & Startups· 26 oct 2023Pódcast · 2 vocesOne Attacker and a For Loop: Why Email Is Still the Softest Target in an AI Arms RacePresenta: Sarah Guo, Elad GilMaterial Security co-founder Ryan Noon on how 2016 election hacks, Google and Microsoft's email duopoly, and large language models are rewriting both sides of cybersecurity.
1:14:36ENCognitive Revolution "How AI Changes Everything"· 13 oct 2023PódcastZulu Bypasses GPT-4, and a Hundred Examples Undo the GuardrailsPresenta: Nathan LabenzNathan Labenz reads seven papers — four hopeful, three not — on whether anyone can actually keep a language model under control.
2:15:11ENCognitive Revolution "How AI Changes Everything"· 22 sept 2023PódcastTwenty Gibberish Tokens Jailbroke ChatGPT and BardPresenta: Nathan LabenzCarnegie Mellon’s Zico Kolter, Andy Zou, and Asher Trockman walk through a universal jailbreak that transfers from open models to commercial APIs, and a training-free way to steal some of pretraining’s benefit.
1:23:10ENCognitive Revolution "How AI Changes Everything"· 19 sept 2023PódcastLuxury Purses Under $500 Beat a Bank's Fraud ModelPresenta: Nathan LabenzArthur.ai CEO Adam Wenchel on boundary attacks, LLM firewalls, and why a model that eats raw text cannot be secured from the inside.
1:20:06ENCognitive Revolution "How AI Changes Everything"· 5 sept 2023PódcastAccuracy Dropped From 93% to 7% — Cryptography Wants to Put a Dashcam on AIPresenta: Nathan LabenzDaniel Kang explains how zero-knowledge proofs could verify that a model ran as promised, and that a user is human, without exposing weights or biometrics.
2:42:44ENCognitive Revolution "How AI Changes Everything"· 11 jul 2023PódcastThe Former Trader Who Writes 10,000 Words a Week Puts AI Doom at 60 PercentPresenta: Nathan LabenzZvi Mowshowitz tells Nathan Labenz why today's language models are a gift, why the default future past human level is extinction or a worthless universe, and who actually moves the AI debate.
1:33:51ENCognitive Revolution "How AI Changes Everything"· 23 may 2023PódcastGPT-4 still writes SQL that will not run. She put a guardrail on the modelPresenta: Nathan LabenzShreya Rajpal built Guardrails AI so developers can encode what “correct” means, validate the pieces, and send failures back to the model instead of hoping the prompt holds.
1:38:22ENCognitive Revolution "How AI Changes Everything"· 19 may 2023PódcastSix days after “slow down,” the plugins went livePresenta: Nathan LabenzConjecture CEO Connor Leahy talks GPT-4, the magic of black-box models, and cognitive emulation as a bounded alternative to god-like AGI.
1:29:59ENCognitive Revolution "How AI Changes Everything"· 20 abr 2023PódcastA College Senior Built a Jailbreak Leaderboard. GPT-4 Was Hardest — Until "Dr. AI"Presenta: Nathan LabenzAlex Albert, a University of Washington computer science senior, tells Nathan Labenz why collecting jailbreaks is a public good, where he would draw the safety line, and how three prompts leaked a system message verbatim.
2:48:12ENLex Fridman· 13 abr 2023Pódcast · 2 vocesThe Asteroid We Are Building OurselvesInvitado: Max Tegmark · Presenta: Lex FridmanPhysicist Max Tegmark tells Lex Fridman why a six-month pause on models larger than GPT-4 is not a ban on AI, but a chance to stop a suicide race.
1:42:48ENCognitive Revolution "How AI Changes Everything"· 13 abr 2023PódcastThe Skype Co-Founder Who Wants a Six-Month Pause on Frontier AIPresenta: Nathan LabenzJaan Tallinn argues that each 10× jump in training compute carries a 1 to 50 percent chance of ending everything, and that the labs still will not say when they will stop.
1:33:49ENCognitive Revolution "How AI Changes Everything"· 4 abr 2023PódcastSafe Only Because It's Weak: A GPT-4 Red-Teamer and Two Founders Debate the PausePresenta: Nathan LabenzNathan Labenz, who spent six months trying to make GPT-4 misbehave, wants labs to stop training anything bigger; Chroma's Anton Troynikov and Lindy's Flo Crivello argue a six-month freeze buys little and may select for the least careful labs.
3:17:51ENLex Fridman· 30 mar 2023Pódcast · 2 vocesWhoops is the sound of getting less wrong: Yudkowsky, two weeks after GPT-4Invitado: Eliezer Yudkowsky · Presenta: Lex FridmanTwo weeks after GPT-4 launched, Eliezer Yudkowsky sat down with Lex Fridman and started by admitting the transformer stack had already gone further than he expected.
1:23:53ENCognitive Revolution "How AI Changes Everything"· 17 mar 2023PódcastGPT-4, 24 Hours Later: No Safety Locks, a Captcha Hire, and a U.S.–China DeadlockPresenta: Nathan LabenzA day after OpenAI shipped GPT-4, ChinaTalk sat a red teamer, a pessimist, and a policy researcher down to argue over capability, safety, and a race nobody can brake.Cargar másMostrando 24 de 179