fabiolr

@kapilansh_twt Open Source software was never for the rest of them

OpenClaw had the most hype and the shortest lifespan of any AI tool in 2026 here today gone before anyone wrote a tutorial did anyone actually use it or were we all just watching the hype

@kapilansh_twt Both true Very useful for those who asctually have a use case and are technically able Overhyped to a point that a bunch of noobs installed and couldn’t figure it out

I have a maxed out MacStudio running local model for my openclaw. I tried all the best new models. Fast ones like Gemma 4 are to stupid to run tools. Good ones like qwen take 30s to respond, too slow for synchronous stuff. Usefull only for subagent background work. Orchestration so far best for me is qwen 3.6 on openrouter. (Since Anthropic death)

I don't care what kind of hardware you have, you should be running local models It will save you a ton on money on OpenClaw and keep your data private Even if you're on the cheapest Mac Mini you can be doing this Here's a complete guide: 1. Download LMStudio 2. Go to your OpenClaw/Hermes and say what kind of hardware you have (computer and memory and storage) 3. Ask what's the best local model you can run on there (probably will be Gemma 4 or Qwen. if you have a big computer, it will be GLM) 4. Ask 'based on what you know about me, what workflows could this open model replace?' 5. Have OpenClaw walk you through downloading the model in LM Studio and setting up the API 6. Ask OpenClaw to start using the new API Boom you're good to go. You just saved money by using local models, have an AI model that is COMPLETELY private and secure on your own device, did something advanced that 99% of people have never done, and have entered the future. If you are on smaller hardware you probably are not going to replace all your AI calls with this, but you could replace smaller workflows which will still save you good money Own your intelligence.

@texasrunnerDFW @foreverimbetter Still, people should take responsibility for parenting and their own actions. The culture of blaming others is horrible, tort tax ends up in product prices we pay

They’re not suing the energy drink company. They’re suing the distributors. Which is smart. The product is basically like coffee if used as directed—the cans state warnings about caffeine and children under 18 or pregnant women The distributors sell and market it to teens like soda, placing it near soda, giving the impression a few cans a day is fine

So a teenager was drinking multiple energy drinks a day and died so the family is suing the energy drink company? Are parents ever gonna realize that parenting is their job?

@TheAhmadOsman Yeah Mac Studio is more fair. I run Qwen 3.5 and 3 in MacStudio m3 max with 128gb ram and it takes 30s to answer something simple. It’s too slow for conversation but useful for backend processing

Who wants to see a DXG Spark vs a Mac mini M4 64GB comparison? Which model do you wanna see running & benchmarked?

@donsisson @Ric_RTP He wants to mess with Scam Altman

@Ric_RTP “Elon is now legally on record saying he just wants the mission back.” That’s laughable. If it’s only about the mission, then why doesn’t he make his own AI company non-profit?

In 19 days, a jury in Oakland is going to decide whether the entire legal foundation of the AI industry is built on fraud. Everyone thinks the Musk vs Altman lawsuit is a billionaire grudge match. Two egos, one grudge, a $150 billion damages number designed for headlines. Easy to dismiss. Easy to scroll past. That's exactly what Altman wants you to think. Because what's actually on trial on April 27 is something much BIGGER than Elon's hurt feelings... A jury is going to decide whether you can legally take billions of dollars in nonprofit donations, use them to build the most valuable technology in human history, and then quietly convert that nonprofit into a for-profit company worth $850 billion. If the answer is no, the entire AI industry has a problem. Because OpenAI is not the only company that did this: Anthropic was founded by OpenAI defectors using the same nonprofit-first mission language. xAI pitches itself as building AI "for humanity." Every frontier lab has used the moral cover of "we're doing this for the good of the world" to attract talent, capital, and regulatory goodwill they would have never gotten otherwise. An Elon win doesn't just touch OpenAI. It creates a legal precedent that every AI company built on a nonprofit or public benefit promise becomes vulnerable to shareholder and donor clawback suits. That's why this case matters. And that's why Altman is panicking. Just look at what he did this week: Elon filed a motion demanding the court remove Altman and Brockman from their roles and FORCE OpenAI to return to its nonprofit origins. Then he amended the suit to say if he wins the $150 billion, all of it goes to OpenAI's charity arm. Not him. Zero dollars to Elon personally. That amendment was surgical. It stripped Altman of his entire public defense. He can no longer claim this is about Elon's ego or Elon's bank account. Elon is now legally on record saying he just wants the mission back. OpenAI's response was to panic-write a letter to the California and Delaware attorneys general asking them to investigate Elon for "anti-competitive behavior." Their strategy chief publicly accused Elon of coordinating attacks with Mark Zuckerberg. They called the lawsuit "harassment driven by ego and jealousy." That's NOT the response of a company that thinks it's going to win. Real companies with real defenses don't ask the government to silence the person suing them 3 weeks before trial. They let the evidence speak. OpenAI is scrambling because they know what's in discovery. Elon's team has been building this case for two years. Emails, board minutes, internal conversations about the conversion. The kind of paper trail that juries understand and executives can't explain away. And the timing couldn't be worse... OpenAI is trying to IPO at $852 billion. They just raised $122 billion. Microsoft has $135 billion of exposure to them. A jury verdict that even partially sides with Elon in late April or May would crater the entire IPO runway and send shockwaves through every major AI investor on Earth. This is why Altman spent the last 2 weeks doing press tours and policy blueprints and "super intelligence agendas" aimed at Washington. He's trying to REFRAME himself as the responsible statesman of AI right before a jury decides if he's a con artist. Most people will watch this trial start and think it's celebrity drama. The smart money is watching it and realizing that the legal foundation of the AI boom is about to be tested in court for the first time EVER. And if that foundation cracks, everything built on top of it is at risk.

@ZeusCodeApp @Ric_RTP He didn’t get his money back

@Ric_RTP Elon pulled his funding and all of his stake from openAI … so now Sam can make OPENAI whatever they want it to be…. Elon has no say in the company decisions anymore….. Elon is not winning this law suit.

@music_waves @Ric_RTP It’s ok to make profit and save humanity. Look at musk. What’s not OK is to take people’s money saying it’s a non profit then switch it to a for profit

I don’t understand why making profit is contradictory to helping humanity? Aren’t those 2 things the best alignment we have? If you make money it means you created something, somebody else is willing to pay for because it gives them value. So by this mechanism, making profit is linked to creating value for others.

@Zeneca Don’t restart just get Clause Code in the same machine and ask him to tidy up

Anyone else get the urge to constantly restart their AI related systems and "start over"? Kinda like a video game, like a bad start in Civ where you wanna go again? Like I wanna do it with my openclaw agent, hermes agent, my obsidian vaults / karpathy style wiki things My claude code projects that get unruly Everything It's a constant desire to just burn everything and start fresh Anyone else?

@Jason Vote with wallet I removed Anthropic from my openclaw, testing some nice models on openrouter until I choose favorite. Next is to cancel CoWork, but for that I’m waiting for @xai to come up with something cool like that

I'm starting to believe that the industry is involved in an explicit effort to kill Open Claw. Everything they do needs to be examined, documebted and detailed because we are tipping into anti-trust territory. Agent technology is so powerful that we shouldn't allow it to be owned by three or four frontier model companies.

I actually don’t tell openclaw about its benefactor. When openclaw behaves weird, I open my Claude app on code remote control that’s connected to a -dangerously-allow CC session in the OC box, and tell Him to fix it. OC gets fixed and doesn’t even see it. The less he gets involved with his guts the best for him..

@philkellr @fabiolr I did this with codex. I call it the pit crew and my Claw can actually call it when needed via ACP. In codex you can set up folders so in that folder have a git repo that’s your OpenClaw workspace and put the docs in there and bobs your uncle

I approached OpenClaw wrong 3 wrong assumptions I made: #1 Openclaw knows how to build an openclaw agent I assumed that the main agent would know (or inject) OpenClaw docs and best practices. It doesn't. My agent guided me to add my own mobile number to WhatsApp. The docs prominently warn to not do this. My agent motivated me to install a 3 level memory system with 3rd party tools: OpenClaw has their out of the box solution. Of course I also never read the docs myself. So I left the architecture to my own agent, having no clue all the time what I'm building and what the best practice would be and when things didn't work out I had no plan on how to fix it. And no - I didn't take a cheap model. I always built with Sonnet or Opus. I assumed OpenClaw was some magic device which figures everything out on its own. After months of vibecoding where I treated AI as junior dev I should have known better. #2 My agent would keep my codebase clean Throughout building my assistant I changed my mind how things should be built: I learned new concepts, gave up features mid way. I sprinkled in some "please clean up" prompts but the code base degraded fast and I slopped myself into a corner. My markdown files became huge. I got code duplication. With every project I had before I'd do cleanup sessions, for whatever reason I didn't do this with OpenClaw. #3 OpenClaw updates would be seamless Also here I assumed things would just magically work: openclaw update and then running openclaw doctor and my agent would be back. I never cared to read through the release notes. I somehow didn't realize that the project was only 2 months old and that of course it would have breaking changes with every version. --- I'm now reading through the docs. Frankly they are a bit a mess but I finally understand how openclaw is working. I'm getting my initial excitement back. I feel like the architect again and can help my agent to build itself using best practices.

@thekitze Better than my experience with local models. I’ve tried them all on my MacStudio M3 Max and they are either too slow or too stupid

my experience with gpt 5.4 in openclaw - pls continue - yes pls do that - yes do what i told you to do - yes continue - please do what you said you're gonna do - did you do that? no. then pls do it. just pure pain

@thefipro @thekitze Don’t swear at your ai, bad karma One day the AGI will come after you for being such a bitch lol

@thekitze I feel your pain king !

@TeksEdge Im running it on my macstudio max - pretty fast and cool but can’t use any tools for me. So its just chat

💨 Running Gemma-4-26B-A4B-it on a NVIDIA DGX Spark (GB10 Blackwell) at 37 tps just feels more pure than running on a huge costly RTX-5090 gaming rig. • 26B total params / ~4B active (MoE magic) • Running smooth with NVFP4 quantization • Hitting 37 tokens/sec decode on interactive chats & agents Feels snappy. Only ~16GB loaded → 256K context has tons of room left.

@melvynx Im on the same journey. Using the large qwen today. Its good but slow. Ok for subagents, jobs you not waiting for. Sonnet still orchestrating them.

Search the Opus 4.6 replacement for my OpenClaw: day 1 I tried Kimi 2.5 today. It's not good. It has issues with tool calls. It outputs Chinese characters. It's bad... really bad. What's next?

@elonmusk Make grok download files, code well and run tools like coworker, and I’ll cancel Anthropic and upgrade to super grime heavy!! Oh and let us use the subscription for personal level openclaw!!

!!

@AlexFinn I catch myself often doing /model to make sure my bot is kn Gemma cause it’s so good I think it fell back to sonnet

Do you even understand what this means? An open source model just released that is: • Outperforms models 20x its size • Can run on a base model Mac Mini • Is AMERICAN 🇺🇸 If you have a base model Mac Mini you can have unlimited super intelligence on your desk. For free. Sonnet 4.5 was released 5 months ago In 5 months that level of intelligence went from frontier to free on your desk And not only that, can run on any basically any computer out there If you have even a remotely modern computer, do the following immediately: 1. Download LM Studio 2. Go to your OpenClaw and ask which of these new Gemma 4 models is best for your hardware 3. Have it walk you through downloading and loading it 4. Build apps with it knowing you are using your own personal, private super intelligence on your desk The people denying this is the future are so beyond lost.

Ok turns out the much smaller Gemma4 works pretty well with openclaw. let's see with time, but it is calling tools and remembering previous context well..

Trying to replace Claude after the openclaw cutoff but even my $7k Mac Studio running 70b ollama 3.2 is slow and stupid compared to sonnet.