Results for “agents”

…scaling. The system card reports scaling up to 100 parallel agents in Section 8.12. @scaling01 called it the first lab report of its kind. @maksym_andr highlighted it as evidence on multi-agent scaling laws. ProgramBench caveats.…

…Analysis’s Stirrup Slack integration, which adds Slack-native agents with documents, subagents, MCP, browser use, and code execution. MCP is not dead; it’s being normalized into production plumbing: Despite a wave of “MCP is dead” jokes…

…Genie 4 as a step toward safe virtual environments for testing agents and robots. Demos: Gemini 3.8 Flash decomposes tasks, checks each step and replans as the scene changes. A Gemini 4 Argon + Genie 4 experiment simulates an Apollo…

…and expert systems to transformers, reasoning models, coding, agents, and recursive self-improvement. He lays out why he thinks this moment is different, why AI is finally escaping the old boom-bust pattern, and why the real bottleneck may …

…adoption, BUT without Goodharting waste? Memory: how are your agents/models improving as your users use them? World Models: how are you solving spatial intelligence and adversarial reasoning? Agentic Commerce: how are agents paying for…

…AI” over your entire email history, how they design tools vs. agents and fight agent laziness, what box-priced inference and local-first caching mean for cost and reliability, and his bet that your inbox will power your future AI EA while…

…cycle point to a meaningful broadening of where and how coding agents run: mobile-first workflows via Codex Mobile walkthroughs, iPad/VPS session management from @npew, Telegram/home-server remote setups from @itsclivetime, and hints of…

…frontier- Planning, abstraction, and calibration in reasoning agents and why these concepts matter- The future of open-source AI models, including DeepSeek, OLMo, and the potential for an “American DeepSeek”- The importance of model…

Note: this is Pliny and John’s first major podcast. Voices have been changed for opsec. From jailbreaking every frontier model and turning down Anthropic’s Constitutional AI challenge to leading BT6, a 28-operator white-hat hacker…

…than pre-training”), why long context will keep climbing but agents + graph walks might matter more than 10M-token windows, the shopping model as a test bed for interruptability and chain-of-thought transparency, why personality toggles…

…LLMs41:36 Building Richer Systems with MCP43:13 Understanding Agents in MCP45:45 Nesting and Tool Confusion in MCP49:11 Client Control and Tool Invocation52:08 Authorization and Trust in MCP Servers01:01:34 Future Roadmap and Stateless…

…+ RL track: Claude 4 + RL chat with Will Brown For SWE Agents: the Factory AI episode For Robotics: our CloudChef pod For Gemini + Voice: our Google I/O pod, released today For Reliable Agents: our chat with Solomon Hykes releasing tomorrow…