Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →
20VC with Harry Stebbingsgestern +173JSJane Streetgestern +119AI Engineergestern +1硅谷101vorgesternMBMatthew Bermanvor 3 Tagen +111PragerUvor 3 TagenY Combinatorvor 3 Tagena16zvor 4 Tagen +1SemiAnalysisvor 4 TagenGOTO Conferencesvor 4 Tagen

Ergebnisse

4 Artikel
Sortieren
KanalMatthew BermanThemaAI SafetyLänge15–30 Min.
3 Folien17:15EN
MBMatthew Berman· 28. Aug. 2026The Hugging Face Incident: AI Evaluation, Sandbox Escape and Reward HackingMatthew Berman · Forward FutureMatthew Berman explains the reported OpenAI evaluation incident and the security and incentive failures it exposed.AI SafetyAI securityCybersecurity+1
5 Folien26:05EN
MBMatthew Berman· 31. März 2025Inside Claude: What Interpretability Research Reveals—and What It Cannot Yet ExplainMatthew Berman · Forward FutureMatthew Berman examines Anthropic’s case studies on multilingual features, planning, arithmetic, hallucinations and safety.AI researchModelle & TrainingAI Safety+1
4 Folien15:34EN
MBMatthew Berman· 6. Jan. 2025Sam Altman on AGI and Superintelligence: A 2025 DiscussionMatthew Berman, Ray Kurzweil, Lex Fridman · Forward FutureMatthew Berman examines Altman’s statements about AGI, the singularity and possible AI-driven scientific progress.AGIAI SafetyAI research+1
2 Folien21:16EN
MBMatthew Berman· 9. März 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.AI SafetySicherheitEvals+1