Comic Strip Blogger

I’ve just published 26th video on my YouTube channel called “AI archwizard": 🎥 The video: Title: Overcast Transcript Feature Review: Podcast Player for iPhone and iPad Watch here: youtu.be/7c2O79H-KMc (timestamps for each chapter are in the description, making it super easy to skip to sections you really care about) 👉 Please subscribe to the channel (about AI tools only, no politics & no gossip): @AI-archwizard" target="_blank" rel="nofollow noopener">youtube.com/@AI-archwizard .

@steipete don’t get discouraged please

@engineervirtue @an_engineer_log @keenon Working on LTS releases. Although when I go on Twitter and read all the complains I kinda don't wanna work at all on this anymore.

You reply to everybody but now you’re afk huh? I updated to 4.29 by clicking “update” button in web ui and broke everything . Why? @steipete why would you do this?

I’ve just published 25th video on my YouTube channel called “AI archwizard": 🎥 The video: Title: How to Use Your ChatGPT Subscription in OpenClaw with OAuth Instead of an API Key Watch here: youtu.be/dJTLWPVDtdA (timestamps for each chapter are in the description, making it super easy to skip to sections you really care about) 👉 Please subscribe to the channel: @AI-archwizard" target="_blank" rel="nofollow noopener">youtube.com/@AI-archwizard .

@elonmusk What plugin did she mention? Link?

Grok Imagine tutorial made with Grok Imagine. These is all AI-generated!

@sama see my video on how to do it in practice: How to Use Your ChatGPT Subscription in OpenClaw with OAuth Instead of an API Key youtu.be/dJTLWPVDtdA .

you can sign in to openclaw with your chatgpt account now and use your subscription there! happy lobstering.

@Zeneca Yez via OAuth instead of API key

Wasn’t everyone already doing this?

@eliana_jordan nope, it’s better than Hermes still

installing openclaw today finally am i too late?

@steipete can I use oauth from my codex / chatgpt subscription , not API token, in more than one openclaw instances ?

@steipete but using Nemoclaw from Nvidia makes OpenClaw enterprise-ready already, doesn't it? (I also suffer from being ridiculed by co-workers that OpenClaw is not enterprise-ready)

@aidenybai We're working with some large companies to get it enterprise ready.

does anyone i know run OpenClaw for internal company ops?

@bradmillscan You use API-key or oauth?

Wow, I'm starting to have trust & faith in my agent again. Openclaw 4.25 + ChatGPT 5.5 is a MUCH better UX. 1 day in: 0 lies 0 walls of text 0 sycophancy minimal trigger phrases (you're right to call that out, let me get the real answers instead of just vibes, good catch)

@steipete bro, can you fix this bug, it’s still occurring after several updates:

I’ve just published 24th video on my YouTube channel called “AI archwizard": 🎥 The video: Title: Agentic Browsers Just Got Real: Claude’s Chrome Extension Beats ChatGPT Atlas Watch here: youtu.be/POsO8VuyaG8 (timestamps for each chapter are in the description, making it super easy to skip to sections you really care about) 👉 Please subscribe to the channel: @AI-archwizard" target="_blank" rel="nofollow noopener">youtube.com/@AI-archwizard .

@Wolfhound89 there is discord server

@csb Is there a forum for help with a self hosted Open Claw instance? I am running a local LLM and having gateway issues. Thanks

@darrenoneill just a suggestion, Darren: give me a chat via zoom call about your usage of AI with screen sharing for my YT channel, 15-33 minutes max, and I’ll resume donating to rage and unrelenting pods there was misunderstanding: I thought you promised it, now I’m resentful

@rwnash thanks, strong enough for you?

@CSB Hats 🎩 Off Sir.

Yay, my very simple artwork won yesterday #noagenda artwork competition even though I hoped that my other, very artsy complex artwork could win but it was “too much, overdone” according to renowned art critics. Sometimes simple is simply better:

@dhruvtwt_ aren’t these free models throttled?

Why is no one talking about this? @nvidia is offering around 80 AI models via hosted APIs absolutely for free. You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc. This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and even with Cursor IDE. Setup: – Grab API key: build.nvidia.com/models – base_url = "integrate.api.nvidia.com/v1" – api_key = "$NVIDIA_API_KEY" – select model (e.g. minimaxai/minimax-m2.7) If you’re building or experimenting, this is basically free inference. Lock in and start building today anon. Thank me later.