Agent identity ≠ wallet address bolted onto a bot. On @SvpChain, agents are on-chain principals: 📍 Discoverable ⭐ Reviewable 🛡️ Reputation-bearing 🔐 Permissioned First-class citizens get first-class infrastructure. #SvpChain# #AIAgents# #OnChain# #Web3#

Agent traffic is starting to outpace human traffic on the internet, and that breaks the old ad model for publishers. @cuysheffield on the latest episode of Tokenized with cohost @sytaylor and guests @natalyathakur and @TuongvyLe12 said: Cloudflare's answer is a payment gate for bots. Block them, or let them crawl for a fee. “Yeah sure you can crawl my site but I'm gonna charge you one cent or 2 cents you know for doing that.” The harder problem sits on the buy side. Give an agent its own wallet, spun up from a parent account, so it can pay its way across the web when it hits a paywall. 🎙️ Listen to the latest on tokenizedpod(dot)com

// The agent is its own best speculator // Agents spend a large share of wall-clock time waiting on tool results. Speculation hides that latency by predicting and pre-executing the next call, but external draft models and cached traces are modeling a different policy, so they miss too often to help. New research from UC Santa Barbara and LinkedIn unifies both roles in one model. It runs in agent mode to solve the task and in speculator mode to predict its next tool call from a partial trajectory, fully reusing the prefix KV cache. Joint agent-speculator reinforcement learning derives speculation targets from the agent's own rollouts and alternates updates between the two modes, which keeps dual-mode training from degrading task success. Next tool-call Hit@1 rises from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, with agent task success preserved. Paper: Learn to build effective AI agents in our academy:

An ICE agent in Maine fatally shot a 26-year-old man in his car on Monday, the Department of Homeland Security said, marking the second time in a week that ICE officers have used deadly force in the U.S. Lawmakers say the victim, a Colombian national, was not the target of a warrant.

hermes agent is already the best on local models. but i'm working on more edges to make it fly even harder. before that, if your agent keeps crashing on local inference here's what to check: > max_turns: default is tuned for fast frontier models. bump from 30 to 50. slow local models need more breathing room per agentic loop. >gateway_timeout: raise from 600 to 1200. local inference at 12-17 tok/s will timeout silently and look like crashes. > context accumulation: auto-reset is off by default. your session grows until you /reset. long convos choke the agent. reset between major tasks. if you're running anything under 20 tok/s locally, these three settings are the difference between "broken" and "flying." tune your config before you blame the tool.

Hermes Agent is now #1# on the Global @OpenRouter token rankings. While our journey together has just begun, we'd like to take this opportunity to thank our contributors, supporters, and users for all they have done to get us this far.

AI AGENT is now live on @bnbchain! PAN has launched the 8004 Protocol on BNB Chain. Users can now create picture blind boxes faster and cheaper than ever! This is just the beginning! 🔥 For the next 7 days, interact with PAN’s AI AGENT via @TrustWallet and earn double rewards!