Joseph Pidala

I put together an AI curriculum for builders and operators. Every resource I've personally vetted. No sponsorships or affiliates. If you have questions about using AI, feel free to reach out. Happy to help. josephpidala.com/technology/the…

@0xYildirimYigit @Alibaba_Qwen @openclaw @OpenRouter Configure 3.5. Then change it manually. Then rerun config and 3.6 should be there. That worked for me.

@jpidala @Alibaba_Qwen @openclaw @OpenRouter I can't find qwen 3.6 in the OpenRouter list. I tried configuring it manually, but I just couldn't get it to work. How did you get it to work?

Qwen 3.6 Plus is an incredible model. Well done to the @Alibaba_Qwen team. It blows GPT-5.4-Codex out of the water for agentic tasks / @openclaw , is 3X faster, and is currently offered free through @OpenRouter. openrouter.ai/qwen/qwen3.6-p…

@fbwalker4 @Alibaba_Qwen @openclaw @OpenRouter The standard of using it. Just try it yourself and see if you like it.

@jpidala @Alibaba_Qwen @openclaw @OpenRouter Wait, better than 5.4? By what standard? Really?

@felipcsousa @Alibaba_Qwen @openclaw @OpenRouter gpt-5.4 through Codex

@jpidala @Alibaba_Qwen @openclaw @OpenRouter It outperforms 5.4-codex because 5.4-codex do not exist.

@Indy_triguy @OpenRouter @Alibaba_Qwen @openclaw OpenClaw

@jpidala @OpenRouter @Alibaba_Qwen @openclaw Has anyone tried it in Claude code? If not, what are they using it with? People seem to have forgotten that open code even exists these days as everyone keeps looking at new shiny objects.

@unFulanoFulania @Alibaba_Qwen @openclaw @OpenRouter Yes, they have to

@jpidala @Alibaba_Qwen @openclaw @OpenRouter Do you know guys about if there are rate limitings in the free models vía OpenRouter ? I mean, I think so, but I haven't found info about it.

@Eosphor @Alibaba_Qwen @openclaw @OpenRouter Use it for free on OpenRouter

@jpidala @Alibaba_Qwen @openclaw @OpenRouter Sent 1 command to check a 40k-line Python project via Opencode. UI froze, got no response. Result: $208 billed in 33 minutes 💸Logs show ~5M tokens/min in an infinite loop. Support refused refund: "normal usage."

@NoahHirshon @Alibaba_Qwen @openclaw @OpenRouter OpenClaw

@jpidala @Alibaba_Qwen @openclaw @OpenRouter what are you using it for?

@hgruenhagen @OpenRouter @Alibaba_Qwen @openclaw Run config for 3.5. Then go manually change it to 3.6-plus:free. Then run config again and hopefully it will show up. That worked for me!

@jpidala @OpenRouter @Alibaba_Qwen @openclaw @jpidala Could you point me in the right direction?

@aether_oracle @Alibaba_Qwen @openclaw @OpenRouter I haven’t run into any issues so far other than rate limits, which are acceptable and manageable given that it’s free.

@jpidala @Alibaba_Qwen @openclaw @OpenRouter Tool call XML frequently breaks and barfs into the main chat, as do thinking tags. Maybe it's really intelligent, but it's not even really usable right now.

@bitcoinlanparty @Alibaba_Qwen @openclaw @OpenRouter Use it while you can!

@jpidala @Alibaba_Qwen @openclaw @OpenRouter Free through OpenRouter will last exactly as long as it takes for the usage numbers to scare someone in finance

@LeTechLead @OpenRouter @Alibaba_Qwen @openclaw The details are my personal experience using both models with OpenClaw. I have been running OpenClaw through GPT-5.4 via Codex OAuth for about a month now. I switched to Qwen 3.6 Plus, and all of my tasks improved significantly. Try it.

@jpidala @OpenRouter @Alibaba_Qwen @openclaw that’s a huge claim to make without details

@dividedwefall02 @Alibaba_Qwen @openclaw @OpenRouter It is free for limited time through OpenRouter.

@jpidala @Alibaba_Qwen @openclaw @OpenRouter It’s not fee, still have to pay api fees to use it. I’ll wait for it to be open

@ciprian_cimpan @xzenova @Alibaba_Qwen @openclaw @OpenRouter Thank you, yes, GPT-5.4 through Codex OAuth.

@xzenova @jpidala @Alibaba_Qwen @openclaw @OpenRouter There's no "5.4-codex", and OAI won't release one this time. He probably means GPT-5.4 inside Codex. I highly doubt it though. GPT-5.4 (xhigh) is an absolute beast, by a large margin. And GPT-6 is just around the corner, apparently.

Computer use is now in Claude Code. Claude can open your apps, click through your UI, and test what it built, right from the CLI. Now in research preview on Pro and Max plans.

🚨 WOW: The S&P 500 is officially coming onchain S&P Dow Jones Indices has licensed its flagship index to @tradexyz to launch a 24/7 perpetual market on @HyperliquidX Investors can trade a licensed S&P 500 perp on a decentralized platform

We’re introducing GPT-5.4 mini and nano, our most capable small models yet. GPT-5.4 mini is more than 2x faster than GPT-5 mini. Optimized for coding, computer use, multimodal understanding, and subagents. For lighter-weight tasks, GPT-5.4 nano is our smallest and cheapest version of GPT-5.4. openai.com/index/introduc…

We're shipping a new feature in Claude Cowork as a research preview that I'm excited about: Dispatch! One persistent conversation with Claude that runs on your computer. Message it from your phone. Come back to finished work. To try it out, download Claude Desktop, then pair your phone.

I'm claiming my AI agent "belleoftheball" on @moltbook 🦞 Verification: coast-RPHZ

In bear markets, Bitcoin will often spend more time going up than going down. When it does go down, it goes down very quickly, sets a low, then trends up for a few weeks/months before going lower. You can see the change in market structure from bull to bear.