BLOG
Meta turned Catching JiTTests into production infrastructure: two test-generation paths, layered false-positive triage, and human-on-the-loop intent review.
Google's open EmbeddingGemma 2 maps text, code, images, audio and video into one 768-d space with 740M params (270M text-only). We unpack modular loading, MRL truncation and on-device RAG.
Xiaomi open-sources MiMo-V2.6 Pro/Flash: 30 live RL steps, ~750k trajectories at $850k/$2.62M; AA Index 46 tops open models, DeepSWE v1.1 gains +17/+14 out of sample; Vibe World, CUA, science and content demos plus 7k+ RL environments released.
The hard problem in multi-agent systems is not making one agent smarter, but deciding how work itself should move. This long-form guide introduces Graph Engineering: use the dependency test to expose fake dependencies, measure latency by critical path instead of total steps, compress deterministically before reasoning, give verifiers a falsification objective, model human approval as an edge rather than a node, freeze rules that sit outside optimization, and adopt five canonical graph shapes plus a paste-ready graph spec template — along with clear criteria for when NOT to build a graph at all.
As an Amazon Associate, we earn from qualifying purchases.
