TechniqueRLHF / Alignment1 recent entries26 May 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-WikiarXiv:2605.25480v1 Announce Type: new Abstract: LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when ev
TechniqueRAG4 recent entries4 Apr 2026LLM WikiKarpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.
TechniqueAgents8 recent entries10 Jul 2026Frontier and Center: Who evaluates the evaluations?Editor’s note: Some of the most interesting questions in AI are being asked by information theoreticians, around how to provide context to an emerging class of AI agents. A few weeks ago, we waded int→29 Jul 2026Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM AgentsarXiv:2607.24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recov→30 Jul 2026WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream FeedbackarXiv:2607.26604v1 Announce Type: new Abstract: Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained in→10 Aug 2026Muse GlimmerMeta's Apache-2.0 30B Muse Glimmer targets local agentic tool use, multi-step coding, and vision, sized to leave headroom on 32GB machines.→24 Aug 2026ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event PredictionarXiv:2608.20920v1 Announce Type: new Abstract: Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory m→26 Aug 2026Using OKF with Knowledge Catalog to serve context for agentsWe continue to iterate on the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. But a big question remains: How can you sha→9 Sept 2026VercelCloud platform and AI tooling company — AI SDK, AI Gateway, Eve agent framework, Sandbox, and Observability used by this wiki’s public Ask surface.→16 Sept 2026Shared Selective Persistent Memory for Agentic LLM SystemsApple paper: keep specs, schemas, tool config, and constraints; drop session traces. Selective shared memory beat both no memory and full history.
TechniqueSafety3 recent entries11 Dec 2015OpenAIAI research and deployment company behind ChatGPT, the GPT model family, Codex, and the OpenAI API — heavily represented in this wiki’s model-releases and safety corpus.→26 Jan 2021AnthropicAI safety and research company (PBC) that builds Claude — reliable, interpretable, steerable systems — and publishes frontier model and safety research.→30 Jul 2026WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream FeedbackarXiv:2607.26604v1 Announce Type: new Abstract: Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained in