←
Josh3,485 posts
Josh avatar

Josh

@RightSideOfAI

Want to help build a more regenerative and ethical AI future?

◷ Joined January 2026▧ 518 Photos and videos
Josh avatar
Josh@RightSideOfAI·Nov 11

Haven't received a trophy for a long time! MiniCPM ambassador trophy received 🫡 Appreciate the sentiment and the acknowledgement from the @OpenBMB team. I look forward to building more products that help with my mission to build AI for the good of humanity and the world. Small models are the way of the future and I'm glad there are labs like OpenBMB who make them a priority. Love to see what the community builds with these small language models.

Post attachmentPost attachment
Josh avatar
Josh@RightSideOfAI·6h

an ode to jensen maybe? lets burn the close source down!

F*CK IT $10 for $500 GLM 5.3 till end of the week

Raffaele Mancini avatar
⟳ Josh retweeted
Raffaele Mancini@RaffoMancio·Nov 17

It started as a weekend project to learn local inference. Now, it's a growing community. Thank you for 1,000 GitHub stars and 100+ forks! A special thanks to all the contributors and everyone who spent time testing and sharing ideas. This is just the beginning!

Post attachment
Josh avatar
Josh@RightSideOfAI·9h

Now that opencode has opened the gates on GLM. GLM 5.3 - orchestrator & auditor Deepseek V4.1 Flash - worker It's far more concise and calm. I love deepseek but god it would go on some wild rides.

Josh avatar
Josh@RightSideOfAI·10h

Jensen should create a new startup. imagine the funding, the connections and things he could build from scratch

Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen

Josh avatar
Josh@RightSideOfAI·10h

it's going quite well. it's been a fun build so far. currently creating a plugin that brings in UI to help non-technical users with design, by bringing in multiple dsh design plugins including @OpenDesignHQ plugins.

Post attachment

I have been making a personal assistant based on DSH. Same thoughts as you, DSH is simple, but complex for majority of users. So I've been trying to build a dsh-assistant that even my mum could use. open to feedback and contributions. i have included chinese translation in the readme for my Chinese followers 🙃 github.com/RegeneratusLabs/d…

Josh avatar
Josh@RightSideOfAI·11h

makes you wonder if it's worth buying lots of hardware now or do we wait for the uncertainty?

Bring on the chinese gpus who don't rely on cuda. 2 years and we will be flooded. china releases the models. the hardware.

Josh avatar
Josh@RightSideOfAI·11h

exciting model, been testing it out today and it's a great model. it's the sort of model I'd tell my mum and girlfiend to use for everyday non-coding tasks. runs great in hermes, fast and cheap. great they released the weights, lets see what the community cooks with it

Hy4 flash is now open-weight, including Hy4 flash-FP8 and Hy4 flash-Base. 224B (12B active), 1M context, natively multimodal. Fast, efficient and built for everyday productivity. It's yours now. And stay tuned for Hy4 coming up next! 🤗: huggingface.co/tencent/Hy4-f… 🐙: github.com/Tencent-Hunyuan/H… 📄: hy.tencent.ai/research/hy4-f… Released under the Tencent Hy License. See full terms here: huggingface.co/tencent/Hy4-f…

Post attachment
Josh avatar
Josh@RightSideOfAI·13h

Biggest data collection scheme ever.

Anthropic will fund your $85,000 salary to build AI tools, no degree required. It's called Claude Corps, a 12-month full-time fellowship from Anthropic and CodePath. What you get: • $85,000 salary • Medical, dental and vision • A full-time job as a CodePath employee • Relocation support if needed • Real AI work on your resume What you don't need: • A degree • A coding background • Years of experience What you do need: • 18+ and early in your career • Two free courses: AI Fluency and Claude 101 (about 6.5 hours total) • Something you built that people used • Some community or volunteer experience The condition: you must be authorized to work in the US. Apply by Jan 31, 2027. Apply here: codepath.org/claude-corps Bookmark it and send it to the friend who keeps saying they want to break into AI.

Post attachment
Josh avatar
Josh@RightSideOfAI·18h

Time to route GLM 5.3 as orchestrator and auditor and v4.1 flash as worker. Also going to put my partner and some of my workers on Hy4 from v4.1 flash for everyday tasks to see if verbosity comes down for the simple tasks

we're bored we're just gonna do phase 2 now $200 of GLM 5.3 usage for $10 have fun

Josh avatar
Josh@RightSideOfAI·18h

This is great news. GLM as the orchestrator V4.1 Flash as the executor.

we're bored we're just gonna do phase 2 now $200 of GLM 5.3 usage for $10 have fun

Josh avatar
Josh@RightSideOfAI·19h

The future. Build your own harness to your liking. Fine tune your model to the harness. The big labs do it already, now it's our time

Introducing Qwen3.8-27B-pi-adapted 🤗 We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter. The results, measured as pass@1: 🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7% 💻 Terminal-Bench 2.1: 39.5% → 55.8% ⚡ 55–62% fewer tool calls per task This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛 Open weights: huggingface.co/harness-hub/Q… Methodology: huggingface.co/blog/harness-…

Post attachment
Josh avatar
Josh@RightSideOfAI·Nov 17

when you get too excited about the GLM 5.3 $100 usage on opencode go.

Post attachment
Josh avatar
Josh@RightSideOfAI·Nov 17

dsh-softshell make your dsh harness more user-friendly. a plugin that strips out the unnecessary front end features the everyday user would never use. suitable for those who are wanting to deliver dsh as a product - custom agent for non-technical clients, friends & family, or a product offering. pulled a lot of reference from the deepseek chat open source that recently landed this makes for a familiar and seamless user experience for those used to a regular chat interface. soften the shell of your dsh. github.com/RegeneratusLabs/d…

1:00
Josh avatar
Josh@RightSideOfAI·Nov 17

could be a good backend reviewer llm.

Operation GLM Phase 1 $100 of GLM 5.3 usage for $10 available to all OpenCode Go subscribers