The traditional tool-calling approach suffers from high latency, manual control flow, and context pollution. With Search as Code, the model composes search primitives: fanning out queries asynchronously, deduping, filtering, joining, and ranking before results hits its context.
RESEARCH
-
Self-Improving Language Models with Bidirectional Evolutionary Search
By
–
Most LLM search still works by sampling more rollouts or extending one path at a time. This paper's bidirectional evolutionary search does it in a smarter way. It breaks the task backward into smaller
-
Who will bring order to AI in the 2020s?
By
–
In the 1940s, von Neumann brought order to computer architecture.
in the 1970s, Codd brought order to database management.
In the 2020s, who will bring order to AI? -
Ethan’s deep dive on xAI’s SOTA video world model training
By
–
This pod was an incredible gift to the community:
— swyx (@swyx) 1 juin 2026
not only our first pod about @xAI, but Ethan really indulged on all our questions on how to train a SOTA Videogen world model, including specific areas (consistent extending/editing, voice) that Grok @Imagine is *still* SOTA,… https://t.co/purQe9Ja81 pic.twitter.com/Sl4AqAt7RAThis pod was an incredible gift to the community: not only our first pod about @xAI
, but Ethan really indulged on all our questions on how to train a SOTA Videogen world model, including specific areas (consistent extending/editing, voice) that Grok @Imagine is *still* SOTA, -
Longmemeval Experiment: Three Ingestion/Extraction Configurations Compared
By
–
longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval)
2) semantic ingestion/extraction (84.8% accuracy, 94.9% retention)
3) semantic ingestion/deterministic extraction (87.6% accuracy, 90.0% retrieval) this was staggered, not -
Grok, Cosmos, and World Models: The Video Agent Moment
By
–
Grok Imagine’s Agent Moment: Cosmos, xAI, World Models, Generative UI, & the Codex Phase for Video! https://
latent.space/p/video-agents @EthanHe_42
, former @xai world model lead and @nvidia Cosmos researcher, explains why AI video may follow the same path as coding agents, how Grok -
M3: MiniMax’s latest model with 1M-token context and agentic reasoning
By
–
M3 is MiniMax's latest model: 1M-token context, native multimodality, and agentic reasoning, built on their Sparse Attention architecture. Try it in Atomic Chat
-
Demucs produced at FAIR-Paris by @honualx
By
–
Demucs was produced at FAIR-Paris by @honualx and collaborators.
-
Microsoft’s Open-Source AI Tool Makes BI Obsolete, Eliminating Expensive Seats and Steep Learning Curves
By
–
Microsoft made BI tools obsolete with one open-source AI visualization tool.
— AlphaSignal AI (@AlphaSignalAI) 1 juin 2026
Most analytics tools lock you into expensive seats and steep learning curves.
Charts require SQL, transformations require code, dashboards require a specialist.
Microsoft Research just open-sourced… pic.twitter.com/UIvqfVYBpqMicrosoft made BI tools obsolete with one open-source AI visualization tool. Most analytics tools lock you into expensive seats and steep learning curves. Charts require SQL, transformations require code, dashboards require a specialist. Microsoft Research just open-sourced
-
Claude kept telling me to go to bed during evals
By
–
was running some evals this weekend and claude kept trying to get me to go to bed