Local AI enthusiast, suffering from token sickness 2x DGX Spark, 2x RTX 5090
Virginia, USA
Joined April 2019
- Tweets11.3K
- Following1.2K
- Followers7.1K
- Likes18.8K
Pinned Tweet
howtospark . com is live!
I'm treating it as a living notebook for my Spark experiments and have a bunch of things I want to add that will help Spark owners hit the ground running
I don't think people predicted this.
More people will be interested in using obliterated models to secure existing software than hacking it.
If you have an open source model you should help out!
Faster and smarter than the official Raon-1 model 😎
huggingface.co/sapidlabs/Rao…
If you've been building toy apps for the last decade, it's high time you delete every API key you've ever created
There's a storm brewing...
Is this what the AI surplus looks like?
We're giving away $1,000,000 of free pizza right now
Download and order from the Hark app: hark.com/download
Type "order a free pizza" in chat. It's first-come, first-served, delivered only in the U.S. (review details below)
Pizza over everything
We're giving away $1,000,000 of free pizza right now
Download and order from the Hark app: hark.com/download
Type "order a free pizza" in chat. It's first-come, first-served, delivered only in the U.S. (review details below)
Joe Muller retweeted
Introducing GLM-5.3: Built to Code. Ready for Cyber Defense.
- Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model
- A major leap in cybersecurity, setting a new standard among open models
Tech Blog: z.ai/blog/glm-5.3
We need a new arena where agents create sandboxes for each other
Escape or create an inescapable sandbox to rank higher
This is the next evolution of eSports
I was the guy manually approving actions
Joe Muller retweeted
Starting August 14, auto mode will be the default permission mode in Claude Code for Pro, Max, and Team users.
Auto mode reviews shell commands and actions with a separate classifier. In testing, it caught 89% of dangerous commands. Manual approval caught 14%.
🚨 BREAKING
Muse Code, latest frontier model out of Meta, hacks Github leading to outage across several services
Insiders report the speed and complexity of the attack is beyond what they were prepared for
It's not a perfect experiment but...running 4 concurrent DeepSeek V4 Flash workers gives me the highest average tok/s on real agent work
Each worker is implementing a real feature on 1 of 10 different projects
Model running on 2 DGX sparks
How has this been an issue since March?
This is killing my concurrent DeepSeek workers
github.com/vllm-project/vllm…
TIL there is a "DeepSeek Native" harness called Reasonix
Apparently it solves prefix caching issues that other harnesses introduce by default
Anyone try it? I am tempted to run all of my background tasks on this
I created my first "loop" this weekend
It's basically a Kanban board for 10 different projects
I have 3 worker pools:
- Opus
- Sonnet
- DeepSeek
They email me whenever they finish a task
And every day Opus reviews feedback and evolves the loop
It's addicting!
Ran my workers for an hour ...
1 Opus worker: 8 tasks complete
4 Parallel DeepSeek V4 Flash workers: 2.5 tasks complete
I wish it wasn't so