o3-mini vs DeepSeek-R1: Which One is Safer?

Поделиться
HTML-код
  • Опубликовано: 7 фев 2025
  • The paper assesses the safety of DeepSeek-R1 and OpenAI's o3-mini, revealing DeepSeek-R1's higher unsafety rate (11.98%) compared to o3-mini (1.19%) using the ASTRAL testing tool.
    arxiv.org/abs/...
    RUclips: / @arxivpapers
    TikTok: / arxiv_papers
    Apple Podcasts: podcasts.apple...
    Spotify: podcasters.spo...

Комментарии •

Следующие
Автовоспроизведение
[QA] Detecting Strategic Deception Using Linear Probes23:41[QA] Detecting Strategic Deception Using Linear Probes
[QA] Detecting Strategic Deception Using Linear ProbesArxiv Papers
Просмотров 16
Should You Use Your Large Language Model to Explore or Exploit?17:06Should You Use Your Large Language Model to Explore or Exploit?
Should You Use Your Large Language Model to Explore or Exploit?Arxiv Papers
Просмотров 67
Talk Africa: DeepSeek and AI in Africa29:13Talk Africa: DeepSeek and AI in Africa
Talk Africa: DeepSeek and AI in AfricaCGTN Africa
Просмотров 60 тыс.
Marvel Rivals | Winter Celebration, Joyful Jubilation01:50Marvel Rivals | Winter Celebration, Joyful Jubilation
Marvel Rivals | Winter Celebration, Joyful JubilationMarvel Rivals
Просмотров 1 млн
Superman - Teaser Trailer Tomorrow00:31Superman - Teaser Trailer Tomorrow
Superman - Teaser Trailer TomorrowDC
Просмотров 1,1 млн
Rory McIlroy, Scottie Scheffler vs Bryson DeChambeau, Brooks Koepka | Crypto.com Showdown Highlights20:22Rory McIlroy, Scottie Scheffler vs Bryson DeChambeau, Brooks Koepka | Crypto.com Showdown Highlights
Rory McIlroy, Scottie Scheffler vs Bryson DeChambeau, Brooks Koepka | Crypto.com Showdown HighlightsBleacher Report
Просмотров 190 тыс.
Jason Segel Breaks Down His Most Iconic Characters28:00Jason Segel Breaks Down His Most Iconic Characters
Jason Segel Breaks Down His Most Iconic CharactersGQ
Просмотров 230 тыс.
DeepSeek R1 Explained to your grandma8:33DeepSeek R1 Explained to your grandma
DeepSeek R1 Explained to your grandmaAI with Alex
Просмотров 1,2 млн
Run Deepseek R1 at Home on Hardware from $250 to $25,000: From Installation to Questions12:42Run Deepseek R1 at Home on Hardware from $250 to $25,000: From Installation to Questions
Run Deepseek R1 at Home on Hardware from $250 to $25,000: From Installation to QuestionsDave's Garage
Просмотров 317 тыс.
Introduction to Deep Research20:16Introduction to Deep Research
Introduction to Deep ResearchOpenAI
Просмотров 488 тыс.
AI Risks No One is Talking About14:09AI Risks No One is Talking About
AI Risks No One is Talking AboutTJ DeVries
Просмотров 58 тыс.
How DeepSeek is Stunning the A.I. World?29:41How DeepSeek is Stunning the A.I. World?
How DeepSeek is Stunning the A.I. World?CGTN Europe
Просмотров 9 тыс.
Where $17 billion has gone in AI54:32Where $17 billion has gone in AI
Where $17 billion has gone in AITechTechPotato
Просмотров 12 тыс.
TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis29:23TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis
TOTEM: TOkenized Time Series EMbeddings for General Time Series AnalysisSteve Brunton
Просмотров 19 тыс.
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry24:20Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometryArxiv Papers
Просмотров 57
From Large Language Models to Reasoning Language Models - Three Eras in The Age of Computation.1:01:24From Large Language Models to Reasoning Language Models - Three Eras in The Age of Computation.
From Large Language Models to Reasoning Language Models - Three Eras in The Age of Computation.Scalable Parallel Computing Lab, SPCL @ ETH Zurich
Просмотров 6 тыс.
✅Накрыла Горная Болезнь 😱 Эверест на Электро-Велосипедах ⚡️НЕРВЫ СРЫВАЕТ⚡️ ДЕШОВКА СЛОМАЛАСЬ⚡️ПСИХАН1:06:09✅Накрыла Горная Болезнь 😱 Эверест на Электро-Велосипедах ⚡️НЕРВЫ СРЫВАЕТ⚡️ ДЕШОВКА СЛОМАЛАСЬ⚡️ПСИХАН
✅Накрыла Горная Болезнь 😱 Эверест на Электро-Велосипедах ⚡️НЕРВЫ СРЫВАЕТ⚡️ ДЕШОВКА СЛОМАЛАСЬ⚡️ПСИХАНKREOSAN
Просмотров 178 тыс.
Avoid The Person Challenge 😱00:49Avoid The Person Challenge 😱
Avoid The Person Challenge 😱Zhong
Просмотров 9 млн
GOOD RANDOMS - My Only Trophy (Official Music Video)02:45GOOD RANDOMS - My Only Trophy (Official Music Video)
GOOD RANDOMS - My Only Trophy (Official Music Video)Brawl Stars
Просмотров 7 млн
КТО ЛЮБИТ БЛИНЫ?? #shorts00:26КТО ЛЮБИТ БЛИНЫ?? #shorts
КТО ЛЮБИТ БЛИНЫ?? #shortsПаша Осадчий
Просмотров 231 тыс.
США начали войну // Скандал на Грэмми // Взрыв в Алых Парусах30:48США начали войну // Скандал на Грэмми // Взрыв в Алых Парусах
США начали войну // Скандал на Грэмми // Взрыв в Алых ПарусахРуслан Усачев
Просмотров 686 тыс.
How Strong is Glass? 💪00:25How Strong is Glass? 💪
How Strong is Glass? 💪Brianna
Просмотров 25 млн
#makeup #makeupshorts #makeuptutorial #shortvideo #makeupartist #makeupreview #trend00:22#makeup #makeupshorts #makeuptutorial #shortvideo #makeupartist #makeupreview #trend
#makeup #makeupshorts #makeuptutorial #shortvideo #makeupartist #makeupreview #trendباتو مارديني | Bato Mardini
Просмотров 372 тыс.
СОЛО СТАРТ после ГЛОБАЛ ОБНОВЛЕНИЯ в РАСТ / RUST5:04:00СОЛО СТАРТ после ГЛОБАЛ ОБНОВЛЕНИЯ в РАСТ / RUST
СОЛО СТАРТ после ГЛОБАЛ ОБНОВЛЕНИЯ в РАСТ / RUSTchistobzden
Просмотров 82 тыс.