Results
19 articlesSort
15:03EN
Matthew Berman· Jun 25, 2026Claude Tag and the Risk of Locking Company Context into an AI ProviderMatthew Berman · Forward FutureMatthew Berman examines Anthropic’s Slack-based assistant and argues that shared AI workers could reshape software, competition and control of organizational knowledge.
1:22:52ENMatthew Berman· May 7, 2026Richmond Alake on Agent Memory, Context Engineering and the Cost of RecallMatthew Berman, Richmond Alake · Forward FutureIn a livestream with Matthew Berman, Oracle’s Richmond Alake explains how agents store, retrieve and consolidate information, and where memory design trades off with caching and latency.
15:00ENMatthew Berman· Apr 1, 2026Claude Code Source Exposure and Lessons About Agent HarnessesMatthew Berman · Forward FutureMatthew Berman discusses the 2026 source-map incident and commentary on instructions, subagents, permissions, compaction and hooks.
1:02ENMatthew Berman· Mar 20, 2026Use Topic Threads to Keep OpenClaw Conversations FocusedMatthew Berman · Forward FutureMatthew Berman suggests separating subjects into sessions to make an assistant’s conversation context easier to navigate.
0:53ENMatthew Berman· Feb 6, 2026Claude Opus 4.6: Coding Claims, Agent Evaluation, and a Longer ContextMatthew Berman · Forward FutureMatthew Berman discusses Anthropic’s February 2026 model launch and a chart of AI task horizons.
14:20ENMatthew Berman· Feb 5, 2026Claude Opus 4.6: Longer Context, Agent Teams and Early BenchmarksMatthew Berman · Forward FutureMatthew Berman reviews Anthropic's February 2026 model launch, its agent features, long-context results and historical pricing.
17:44ENMatthew Berman· Jan 17, 2026Recursive Language Models: Extending Long-Input Work Beyond a Context WindowMatthew Berman · Forward FutureMatthew Berman examines an MIT research approach that lets language models inspect external text and make sub-calls, along with its benchmark and cost tradeoffs.
8:42ENMatthew Berman· Oct 22, 2025DeepSeek-OCR and the Idea of Visual Context CompressionMatthew Berman · Forward FutureMatthew Berman examines a 2025 OCR model and the possibility of representing document text with fewer vision tokens.
11:38ENMatthew Berman· Aug 13, 2025AI News in August 2025: App Store Dispute, Claude’s Long Context and New ModelsMatthew Berman · Forward FutureMatthew Berman reviews the Musk–Altman exchange, Claude Sonnet 4’s million-token beta, Skywork’s interactive world model and other AI announcements.
21:16ENMatthew Berman· Apr 14, 2025GPT-4.1, Mini and Nano: Coding, Long Context and 2025 API PricingMatthew Berman · Forward FutureMatthew Berman reviews OpenAI’s April 2025 model launch, selected coding benchmarks and demonstrations, and a sponsored Box evaluation.
18:23ENMatthew Berman· Apr 7, 2025Llama 4 Reactions: Benchmarks, Long Context and Early TestsMatthew Berman · Forward FutureMatthew Berman reviews early industry reactions to Meta's Llama 4 release, from benchmark and price comparisons to long-context claims and local inference.
23:52ENMatthew Berman· Sep 4, 2024AI News in September 2024: Compute Clusters, Agents and AI PaymentsMatthew Berman · Forward FutureMatthew Berman reviews early reports on future models, a Minecraft simulation, mixed-reality devices and agent transactions.
27:37ENMatthew Berman· Jun 17, 2024Leo Pekelis on Extending Llama 3 to a Million-Token ContextMatthew Berman, Leo Pekelis · Forward FutureGradient’s chief scientist explains long-context training, coding use cases, inference costs and why retrieval benchmarks tell only part of the story.
0:59ENMatthew Berman· Apr 10, 2024Anthropic’s Many-Shot Jailbreaking ResearchMatthew Berman · Forward FutureMatthew Berman explains a 2024 study on how long sequences of examples can make some language models more likely to bypass safety safeguards.
18:47ENMatthew Berman· Apr 7, 2024What 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.
30:39ENMatthew Berman· Feb 25, 2024NVIDIA’s GEAR Research, Gemini 1.5 and Fast AI InferenceMatthew Berman · Forward FutureMatthew Berman reviews embodied-agent research and a February 2024 set of AI releases and demonstrations.
32:14ENMatthew Berman· Oct 20, 2023MemGPT: Managing LLM Memory Beyond a Fixed Context WindowMatthew Berman, Charles Packer, Vivian Fang · Forward FutureMatthew Berman reviews the 2023 research, demonstrates document retrieval and hears from authors Charles Packer and Vivian Fang about their plans.
7:05ENMatthew Berman· Jul 2, 2023Aider’s Early Coding Assistant: Snake and an Existing Rails ProjectMatthew Berman · Forward FutureMatthew Berman demonstrates the terminal tool’s 2023 workflow, from generating and iterating on a game to proposing a dependency change in a repository.
5:11ENMatthew Berman· Apr 25, 2023AI Memory in 2023: Long Context, Retrieval and Recurrent MemoryMatthew Berman · Forward FutureMatthew Berman compares external agent memories with a recurrent-memory research experiment, and explains why longer context remains a limited result.