Builder, operator and investor. Infra, AI, and product nerd. Opinions are my own. Checkout @lunaroute_ai (https://nitter.gq/t.co/YlZrgrIUKq) to stop caring about token limits
Joined April 2007
- Tweets15.7K
- Following4.4K
- Followers1K
- Likes14.6K
Checkout @opencomputerHQ - they have been cooking some interesting things lately!
Introducing @computer.
Claude Code & Codex in the cloud, as fast as your local machine. Sometimes even faster!
Try it today via Slack, byo sub supported.
opencomputer.dev
If an AI model refuses to help you investigate a vulnerability in your own code, that's a problem.
Security teams need to explore, test, fail, and try again. We're working on giving them models that can actually help, with verified access and without worrying about the token meter.
Curious to see how far we can push this.
Security teams shouldn't hit AI refusal walls when trying to protect their systems.
Introducing LunaRoute Cybersecurity & Cyberdefense.
🔍 Vulnerability research & testing
🛡️ Threat analysis & defense
Reduced-refusal models. Verified access. No token meter.
lunaroute.com/blog/introduci…
Look at the throughput that Vera Rubin can do even on a large model as Kimi K3, it's insane:
nitter.gq/SemiAnalysis_/status/2…
Remember what I said, even Vera Rubins have the same amount of HBM memory (at the current version) as B300 - so bigger models (think Kimi K3.1, Qwen 3.8 Max and future models) that are close or over 3T params are no longer capable of running on a single node, unless quantization and other tricks are deployed.
BREAKING NEWS🚨: NVIDIA just submitted its first Rubin NVL72 Kimi K3 submission, and it can reach over 850 tok/s/user, even at 2.8 Trillion parameters, with over 3x higher throughput on @vllm_project!
Great work by the NVIDIA team, and excited for Rubin Software 1.0 GA coming soon!
Sometimes you just want to scratch your own itch.
I wanted a way to read Markdown in the terminal, including Mermaid diagrams, tables, and images, without having to open a browser or an editor.
Having practically unlimited tokens through LunaRoute makes these little experiments much easier to justify. You can just build what you need, iterate until it works the way you want, and share it with others.
Blog post: eran.sandler.co.il/post/2026…
Eran Sandler retweeted
1/ I've been having lots of fun lately, letting my curiosity lead me down rabbit holes. This is one experiment I've been working on - trying to answer if AI models have distinctive design taste.
We're launching the largest AI design experiment today - uipalooza.ai where you can compare the design capabilities of different AI models side-by-side.
Eran Sandler retweeted
5/ Credit where credit is due - @erans' project @lunaroute_ai flipped the bit for me on using AI without worrying about token cost thanks to their concurrency based billing.
1/ Everyone's framing 3T-param open models as a compute milestone. They're not. They're a memory bill and that bill is why frontier open weights live in the datacenter, not on your desk.
A thread on what it actually takes to serve Kimi K3.1 Pro: 🧵
9/ What would actually move the line: cheaper HBM, credible 2-bit quant, Engram-style memory in a flagship model, or CXL memory pooling across nodes.
Any one of those changes the math. None of them ship this quarter.
Very unpopular thought: software patches at this scale (PHP) and others are the reason you want to pay for a SaaS vendor. It's their job (and legal responsibility!)
Eran Sandler retweeted
Write On 1.1.0 is out: my open-source Mac take on @jasonfried's Write On app concept.
New: AI trims ghost your words instead of deleting them, so any cut can be revived. Plus a model picker and a round of fixes that make the AI features more reliable.
github.com/joeysim/write-on-…
1/3 The Stallman printer story has been on my mind. Xerox at MIT kept jamming - you only found out walking to the printer. He wanted to fix it like he had before. Xerox said no source code. That frustration helped start free software.
2/3 Open source gave us the code. Still meant you had to know C, know the kernel, have a week to learn a codebase for a small fix. So you didn't. I just wanted my webcam's FOV to work on Linux.
3/3 Asked Codex to rip apart Anker's Mac app. 30 min later I had a Linux tool.
Wrote about it - and why we built LunaRoute (@lunaroute_ai):
eran.sandler.co.il/post/2026…
