董子 · 志民⛓️
2.1K posts





AI weather bot turned $240 → $82K on Polymarket weather markets trained my agent, based on bot 2K trades, to build it from scratch installed it on VPS, plugged weather API + Opus 4.7 & gave it Polymarket acc in 2 days he found 2x - 400% ROI trades run your agent in 5 steps: • set up a VPS on Hetzner - $5.99 • plug weather API on {visualcrossing} - free • run Hermes agent using one-liner code - free • connect TG bot + Opus 4.7 • promt {weather trading logic} from article to agent hermes is a self-trained agent, it needs enough trades {50-100} to build the best trading setup start small {$2-$3} limit per trade across 20 weather markets, and let the agent do the rest bot used for traning: @automatedAItradingbot?via=following" target="_blank" rel="nofollow noopener">polymarket.com/@automatedAItr…
my agent: @hermesweather?via=following" target="_blank" rel="nofollow noopener">polymarket.com/@hermesweather… In 2 days, the bot already made 2 trades with +400% ROI and keeps improving quality of trading


BREAKING: Google DeepMind has assembled a strike team because Anthropic is mogging them on coding Led by Sergey Brin and DeepMind CTO Goal: Force recursive self-improvement by turning coding models into full AI researchers that can automate the entire R&D loop GDM is focusing on: >long-context coding tasks >training models on GDM’s private codebase “To win the final sprint, we must urgently bridge the gap in agentic execution and turn our models into primary developers” ACCELERATE



Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…














