mr-t | Bolt Liquidity | Ark Protocol

Open Sourcing something I built a few weeks ago, and haven't gotten around to doing so yet. Meet VibeShare.Cool Peer-to-peer AI subscription sharing for Mac. No central server. Just you and the boys routing Claude/Gemini/etc. straight between each other.

In DeFi, people love chasing APR. But execution can save you more money than the yield you’re farming. A 1% difference on every trade compounds fast. Bad slippage, shallow liquidity, or inefficient routes can quietly drain your PnL. FlowX Aggregator solves this by routing through the deepest liquidity on @SuiNetwork, not just the closest pool. Better execution today means better returns tomorrow.

spent yesterday trying to run qwen 3.5 9b locally on my mac mini m4 for my @openclaw bot. inference is fast (14 tok/s), tool calling works, ram is tight but manageable at 6.6gb. one dealbreaker: ollama forces thinking ON for all qwen 3.5 models. 800+ invisible tokens before any output. 30-60 seconds of silence on every message, even "say hi." what I tried: → think: false on /api/chat - works, but openclaw doesn't send it → reasoning_effort: "none" on /v1/ - disables thinking but breaks tool calling → node proxy to inject the param - works for raw calls, breaks streaming → system prompt tricks - qwen 3.5 ignores them → /nothink suffix - that's qwen 3, not 3.5 reverted to glm-5 for now. the model runs great, ollama just won't let me turn off thinking for small models despite qwen's own docs saying it should default to off. if you're running qwen 3.5 locally with ollama and have thinking disabled with tool calling intact, what am I missing? modelfile trick? different runner? different approach entirely?

Today we’re proposing something big for the Cosmos ecosystem. We’re bringing Osmosis directly into the Cosmos Hub. If approved by governance of both chains, the Osmosis DEX will be migrated natively on the Hub — unifying liquidity, governance, and security under one chain. This proposal reflects a natural evolution for Cosmos: sovereign experimentation followed by consolidation once infrastructure has matured. Osmosis has served as the primary liquidity venue of Cosmos since 2021. Now it has the opportunity to become native infrastructure of the Hub itself. OSMO holders would have the ability to convert to ATOM through a structured migration process, allowing the Cosmos to finally align around a single coordination asset. Finally, ATOM will have its first true revenue stream and direct exposure to the liquidity engine of Cosmos. For years the question has been: how does ATOM capture value from ecosystem activity? This proposal is our answer. Governance discussion begins today. Forum proposal ↓ forum.cosmos.network/t/proposal-dra…