WSJ’s Ryan Felton takes the Fiat Topolino, a super-small EV that costs around $15,000, on a day-long test drive through Ann Arbor, Mich., to see how it stands up to American roads.

High volatility requires serious tooling. That’s where our next partner spotlight @InsilicoTrading comes in. A low-latency terminal that unifies your CEX and DEX accounts into one customisable interface. Stacked with institutional order types (Chase, Swarm, TWAP, Scale) plus a DOM and CLI that used to be reserved strictly for pro desks. Giving everyday traders the exact tools needed to front-run the markets. The partnership has been everything! Cheers to what we built together 🤝 🔗

🤔 Does the communication topology for LLM multi-agent systems really need to be generated from scratch every single time? A team at UCLA questioned that very assumption. Title: Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems URL: ❓ Why have people assumed agent communication topologies need to be searched by a generative model every time? 💡 Turns out they may not need to be. The topologies that survive reward filtering converge to only about 6 distinct graphs, even as the codebook size grows from 8 to 64 — the design space is far smaller than it looks. ❓ Wouldn't making the graph sparser (fewer edges) cut down token usage? 💡 The opposite happens. Edge count correlates with token cost at r=-0.4 — sparser graphs actually use more tokens. Structural "cheapness" doesn't match measured cost. ❓ What's wrong with scoring candidate topologies using a GNN, as prior work does? 💡 For homogeneous agent teams (common in real deployments), the GNN's message passing treats every adjacency matrix as the same input, so it can't tell candidates apart — a real failure mode, not just a minor gap. ❓ So how well does Codebook Agent actually work once it swaps generation for selection? 💡 By compressing topologies into 16 codes via a VQ-AE and picking candidates with a reward-weighted MLP plus a proxy trained on real measured costs, it cuts generation latency from 301-396ms down to 2.4ms — a 125-158x speedup — while improving accuracy by 1.6 points on average over the prior best method and cutting tokens by 21.9-33.2%. #MultiAgent# #LLM#