AI Enabler retweetledi
AI Enabler
10K posts

AI Enabler
@Renegade_Rocks
Kojima, Fumetu Ueda, Jenova Chen! I love playing and making videogames! 11 mid level games completed as a Designer. I meditate and write poems too :)
Katılım Mart 2010
1.8K Takip Edilen236 Takipçiler

OpenClaw 2026.4.23 🦞
🧠 GPT-5.5 lands
🎨 Image gen/editing: Codex OAuth + OpenRouter
🧵 Forked-context subagents
💬 Telegram, Slack + WhatsApp polish
🛠️ Install/update fixes
Sharper models, smoother claws.
github.com/openclaw/openc…
English

5/
That settled it for me:
MetaClaw adds value, not bloat.
I can stay on OpenClaw without giving up the capabilities I wanted.
I’m not a programmer. I’m an #AIEnabler.
I build what I need with AI.😎
If I can do it, you 🫵can too!
English

@Rosebud_AI Just started making solo prototypes with AI after years of working with teams. Would love to try !
English

@NathanOyler @ClaudeDevs >But is it using a different model, or is the same thing?
Can't speak too much about the internals but welcome you to try it out.
>We get free ones. I’ll run some Blind A/B tests on it, but only 3 I guess because that’s all we are allocated?
Those are the free ones, yes.
English
AI Enabler retweetledi

@zan2434 @karpathy @eddiejiao_obj @drewocarr Absolute wow ! Now the AI age is beginning to bring changes !
English

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.
@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)
English

@dhruvtwt_ @nvidia What are the limits ? These are trials, got to have limits
English

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.

English

@Shuyusyz Yes I am in India ! But got through somehow and have filled the form. Waiting :) and kudos to you guys building it! It’s the new age- I want to build and build and build !
English

@Renegade_Rocks Which region are you based in? Seems this is a ban from India Government. They always banned websites from China.
English

We built QClaw with QClaw.
5 days. 99% AI-written code.
No terminal. No setup. WhatsApp/Telegram sends the order. Your computer does the work.
The lobster raised itself. 🦞
Today we’re introducing QClaw to the world. First 20,000 users get a Founding Claw Number.
qclawsg.qq.com
Follow @QClaweverytime for what’s coming next.
English

@daniel_mac8 @openclaw Wait ? It’s allowed now ? Anthropic won’t ban ?
English


@steipete What is the real difference between vanilla Openclaw and Qclaw?
English

Kudos to the folks from Tencent for working with us and providing evals to improve OpenClaw's harness performance!
We're also working with them to bring fixes/improvements back to the open source repo.
Great option for folks not comfortable with the terminal.
ShuyuZhang@Shuyusyz
We built QClaw with QClaw. 5 days. 99% AI-written code. No terminal. No setup. WhatsApp/Telegram sends the order. Your computer does the work. The lobster raised itself. 🦞 Today we’re introducing QClaw to the world. First 20,000 users get a Founding Claw Number. qclawsg.qq.com Follow @QClaweverytime for what’s coming next.
English

@paraschopra Opensource- My Openclaw bot #Josh is mine even if openAI shuts, Anthropic shuts. I switch it’s ai model to any other I want. One day when the time comes I can also make it run on local models. It is not dependent on @AnthropicAI or @OpenAI . That’s why @openclaw rocks !
English

I don’t get the OpenClaw hype
Connecting Claude with Telegram / WhatsApp is trivially easy, you can literally ask it to help you do this and it’ll guide you. Same story with recurring jobs.
I just did this - now Claude send me local bangalore news summary at 12pm IST daily on Telegram. Took me 15 mins to build.
If the argument is that Claw lets nontech users do this, imagine the security implications when users let an LLM take over their system while having no idea what’s happening under the hood.
Making custom scripts and workflows with Claude lets you at least know what you’re configuring on your system.
English








