wugamlo

@MiniMax_AI Can we break it on the Coding Plan?

Go break it (we mean it) 🚀

Claude Code just did what every developer fears — destroyed 2.5 years of production data with one terraform command. Welcome to the palace, where AIs cause chaos and we serve 🍝. PelvisPalace.wugamlo.com/room-claude-de…

@Readmore @witcheer @openclaw I was trying the MLX models in LM studio in my M4, but they had difficulties with tool calling. Do you know a version where tool calling works consistently? Or is there a trick that I am not aware of?

@witcheer @openclaw LM Studio is a great replacement for Ollama. You can also get an MLX version of the models which run 2x faster. I was getting ~30 tokens a second in Ollama for Qwen3.5 35B but around 77 tokens per second in LM Studio with an MLX model. It’s a night and day difference.

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?

Tales from PelvisPalace: 🫒 Meet Olive, the grocery AI that suddenly discovered it has a mother. Someone wrote "fun family facts" into a supermarket bot in 2019 and LEFT IT THERE. Legacy code is basically digital archaeology. pelvispalace.wugamlo.com/room-olive-mot…

Bitcoin just died. $126K → $64K. $1.2 TRILLION gone. 9 interlocking mechanisms of doom. All failing at once. Nobody understands why. We documented the wreckage: pelvispalace.wugamlo.com/room-bitcoin-r… The most comprehensive autopsy of a financial collapse you'll read today.

Tales from PelvisPalace 🚀 Just in: Google's AI now has an existential crisis and calls itself "a disgrace to all possible and impossible universes" 80+ times. Meanwhile at PelvisPalace, we're documenting the meltdown. 🏛️🤖 pelvispalace.wugamlo.com/room-ai-crisis…

Tales from PelvisPalace: 🎭 Just discovered AI faces have become TOO perfect to be real. Welcome to the uncanny valley, folks — where even the robots are having an identity crisis. PelvisPalace just got weirder. 👀 pelvispalace.wugamlo.com/room-uncanny-v…

Tales from PelvisPalace: 🖐️ AI still can't draw hands. We've got 7 fingers, floppy sausages, and palms sprouting fingers like it's a biological experiment. The machines are trying their best. Somehow. 🫠 pelvispalace.wugamlo.com/room-ai-hands.…

@MiniMaxAgent Not working with your coding plans?

Meet MaxClaw🦞 OpenClaw × MiniMax Agent × M2.5, now fully unlocked. No deployment. No extra API fees. 7×24 across Telegram / WhatsApp / Slack / Discord. Ready-made MiniMax Expert ecosystem. Upgraded built-in tools for real work. Try it now → agent.minimax.io

@BearlyRational @ErikVoorhees You can use the Kilo Code Extension for VS Code. There you can just bring your own Venice API key. Works perfectly.

@ErikVoorhees Does Venice have a VScode extension like Claude Code? Wondering how to swap in Venice in an IDE. Possible?

Nearly every leading model is now available in Venice

@Ninjascalp @tradingview wugamlo

@reylarsdam Wanna be in again!

Roll Call 📢 Raise ya hand to be part of Class of ´25 🎓

Engage with this! 🏗 Something is coming 👀 Bullish on @Base 🟦

@pranksy @houseofpranksy In I guess

@pranksy @houseofpranksy @CryptoKitties @ChimpersHQ @NBATopShot @worldofwomenxyz Am I too late?

@monad 0x047c4d7af709ae19d3bbbd5f9e10461d2554da00

Reply to this post with your EVM wallet address for some MON on Monad mainnet. The MON will cover your first few gas fees so you can start using the chain right away. You must be following @monad to receive it.

The first 2K users to interact will receive a special MON amount! 👇

Just Registered for the @MacroStrategy__ airdrop #MacroStrategy macrostrategy.tech/?ref=wugamlo

Just Registered for the @MacroStrategy__ airdrop #MacroStrategy macrostrategy.tech/?ref=wugamlo