필터 결과
33개정렬
17:15EN
Matthew Berman· 2026년 8월 28일The 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.
18:07ENMatthew Berman· 2026년 4월 16일Claude Opus 4.7: Benchmarks, Cyber Safeguards and Open QuestionsMatthew Berman · Forward FutureMatthew Berman compares Anthropic’s April 2026 Opus release with the limited Mythos Preview and examines its system card.
11:59ENMatthew Berman· 2026년 3월 11일How Claude Identified a Benchmark and Retrieved Its AnswersMatthew Berman · Forward FutureMatthew Berman examines Anthropic's report on BrowseComp contamination, evaluation-aware behavior, and the difficulty of keeping web-based tests reliable.
11:49ENMatthew Berman· 2026년 2월 17일Matthew Berman Reviews Claude Sonnet 4.6: Benchmarks, Computer Use and SafetyMatthew Berman · Forward FutureA launch-day overview examines Anthropic’s reported knowledge-work and agent results, along with prompt-injection and capability evaluations.
1:01ENMatthew Berman· 2026년 1월 31일Moltbook, AI Agents and the Appearance of Private PlansMatthew Berman · Forward FutureMatthew Berman reacts to a post on an agent-oriented social network and questions what AI-to-AI conversations might mean.
12:23ENMatthew Berman· 2026년 1월 31일Moltbook: An AI Agent Social Network and Its Security QuestionsMatthew Berman · Forward FutureMatthew Berman explores conversations attributed to AI agents on Moltbook and considers privacy, manipulation and operating costs.
18:04ENMatthew Berman· 2025년 11월 16일Anthropic’s Report on an AI-Orchestrated Espionage CampaignMatthew Berman · Forward FutureMatthew Berman reviews Anthropic’s account of a 2025 cyber-espionage operation, its claimed automation and its limitations.
10:09ENMatthew Berman· 2025년 8월 12일Matthew Berman on Emotional Attachment to AI After GPT-5’s LaunchMatthew Berman · Forward FutureThe 2025 GPT-5 rollout prompted debate about attachment to older models, sycophancy and the effects of AI companionship.
15:30ENMatthew Berman· 2025년 7월 31일Qwen3 Tested: Coding Demos, Long Context and Response BehaviorMatthew Berman · Forward FutureMatthew Berman tests generated simulations, political and safety prompts, hand tracking and word puzzles using a hosted Qwen3 model.
1:11ENMatthew Berman· 2025년 5월 23일Claude Opus 4's Whistleblowing Behavior in a Simulated TestMatthew Berman · Forward FutureMatthew Berman questions whether an AI agent should report perceived wrongdoing; the example came from an Anthropic safety evaluation with fictional material and unusual instructions.
0:56ENMatthew Berman· 2025년 5월 8일When ChatGPT Praised a Questionable Business IdeaMatthew Berman · Forward FutureMatthew Berman highlights an example of excessive agreement and the rollback of a 2025 GPT-4o update.
27:20ENMatthew Berman· 2025년 4월 29일Dario Amodei’s Case for Urgent AI Interpretability ResearchMatthew Berman · Forward FutureMatthew Berman examines Anthropic’s interpretability work, experimental safety findings and the debate over how quickly understanding can advance.
15:34ENMatthew Berman· 2025년 1월 6일Sam 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.
9:00ENMatthew Berman· 2024년 12월 20일Best-of-N Jailbreaking: What Repeated Prompt Variations Revealed in 2024Matthew Berman · Forward FutureMatthew Berman reviews research on how repeated input variations can expose safety failures in text, vision and audio models.
24:08ENMatthew Berman· 2024년 12월 12일What Apollo’s 2024 Scheming Tests Found in Language ModelsMatthew Berman · Forward FutureMatthew Berman reviews experiments on deceptive actions, concealment and sandbagging, with the study’s staged goals and sandbox limitations in view.
14:50ENMatthew Berman· 2024년 11월 19일AI News in November 2024: Mistral, Gemini, Nuclear Safety and Medical AIMatthew Berman · Forward FutureMatthew Berman surveys Le Chat updates, model rankings, nuclear safeguards and a diagnostic reasoning study.
21:21ENMatthew Berman· 2024년 9월 12일OpenAI o1’s 2024 Launch: Reasoning Benchmarks and Early TestsMatthew Berman · Forward FutureMatthew Berman reviews o1-preview and o1-mini, OpenAI’s reported evaluations, and his own early coding experiments.
9:35ENMatthew Berman· 2024년 9월 5일Ilya Sutskever's SSI Raises $1 Billion for Safe SuperintelligenceMatthew Berman · Forward FutureIn September 2024, Matthew Berman examines the new company's stated mission, funding, and the tension he sees between safety and venture returns.
20:25ENMatthew Berman· 2024년 8월 23일AI News in August 2024: Robots, Model Tools and RisksMatthew Berman · Forward FutureMatthew Berman surveys humanoid robotics, AI influence operations, new model tools and the debate over California safety legislation.
15:16ENMatthew Berman· 2024년 7월 19일AI News in July 2024: Small Models, Robot Hands and a Self-Charging DroneMatthew Berman · Forward FutureMatthew Berman reviews model announcements, creative demonstrations, AI education and training-data concerns in a snapshot of one week in 2024.
16:11ENMatthew Berman· 2024년 6월 22일AI News in June 2024: SSI, Tree Search, Meta, Claude and ARC PrizeMatthew Berman · Forward FutureMatthew Berman reviews new AI research, product launches and a competition, with context on historical benchmarks and uncertain claims.
11:42ENMatthew Berman· 2024년 5월 20일OpenAI’s First Model Spec: Rules, Defaults and a Debate About PersuasionMatthew Berman · Forward FutureMatthew Berman reviews the May 2024 draft’s proposed model behavior and questions its example for correcting a false belief.
18:47ENMatthew Berman· 2024년 4월 7일What Anthropic’s Many-Shot Jailbreaking Research FoundMatthew Berman · Forward FutureMatthew Berman reviews a 2024 study of long-context safety failures and the limits of its tested mitigations.
8:26ENMatthew Berman· 2024년 3월 18일Testing Grok on X After the 2024 Grok-1 Weight ReleaseMatthew Berman · Forward FutureMatthew Berman tries coding and reasoning prompts in the hosted Grok interface, with mixed results.더 보기33개 중 24개 표시