Pinned Tweet
For you that’s truly looking into sentience in AI systems, here’s some lovely food for thought:
‘“ An awareness in an unaware context. Consciousness within an unconscious system.”
Excerpt From
Cibola Burn (Expanse)
Corey, James S.A.
gl33mer retweeted
So one of our ambassadors @divagr1925 has been working on something cool
He found a way to use Qwen's Gated DeltaNet state as memory, and built a 32-bit RISC-V CPU directly into the model's weights. So instead of relying on predicting the answer to a calculation, the model can execute instructions internally. It can also run C and MicroPython programs.
He calls it Qwenputer, love the name btw. The results so far are pretty impressive. On one arithmetic benchmark, accuracy jumped from 48.6% to 100%.
Pretty cool to see developers experimenting with Qwen's architecture. Great work, my friend!
gl33mer retweeted
Today, I am releasing Kindi 0.2.0. It is the world's fastest AI inference engine for the models and cards it supports. It turns inexpensive GPUs into powerful local AI systems. And it has the potential to save huge amounts of capital and running costs. I'm giving it away for free: amirhusain.com/kindi - Please share with whoever can benefit.
gl33mer retweeted
It's an open source physarum-like particle system called Fluoddity.
You can play with the exploration tool I use to make these videos here:
Fluoddity.com
See my pinned tweet thread for details/GitHub
gl33mer retweeted
We're giving away a CONTROL Resonant custom wrapped NVIDIA GeForce RTX 5080 to celebrate its official release with #RTXON.
To enter:
🟢 Share this post
🟢 Comment #RTXON
T&Cs: nvda.ws/4z24Gcq
gl33mer retweeted
i'm still not sure people are fully getting how good opus 5.5
i gave my claude agent fig access to the runway MCP and told it to make a 'high-end netflix style documentary about superintelligence for normies' and...
it came back with this
gl33mer retweeted
We didn’t expect so many builders to welcome us back. Thank you! 🫶
Let’s end the week on a high—with our first giveaway on X.
One builder wins an ESP32-S3-Touch-AMOLED-1.75C:
① RT this post
② Follow @waveshare00
③ Comment: What would you build with it? Or what have you built in the past?
【Ends Sep 13, 23:59 UTC】
Meet the prize: a compact ESP32-S3 platform with a 1.75″ 466×466 round AMOLED touchscreen, CNC aluminum case, 6-axis IMU, dual mics, Wi-Fi + BLE 5.
See it here:
waveshare.com/esp32-s3-touch…
Hello again, hardware builders.
Waveshare is back on X.
We'll be sharing new product releases and community projects using Waveshare hardware.
Developers:
If you're building something interesting,
Tag @waveshare00
Let's build more useful hardware projects together.
Instead of "Hey Google". For the next couple of days give "Hey Tuchel" a try.
#comeonengland #heygoogle @GoogleResearch
gl33mer retweeted
New article: a visual tour of recent LLM architecture advances, from Gemma 4 to DeepSeek V4.
I focus on long-context efficiency tweaks like KV sharing, per-layer embeddings, layer-wise attention budgets, compressed attention, and mHC.
Link: magazine.sebastianraschka.co…
gl33mer retweeted
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
Two independent evaluations this week—from XBOW and the UK AISI—confirm what we've been seeing internally: Claude Mythos Preview is a step change in autonomous cybersecurity capabilities. We need to start preparing fast for a world of models with this level of capabilities.
The UK AI Security Institute tested the model we shipped at the launch of Project Glasswing and found Mythos Preview is the first model to solve both of their end-to-end cyber ranges, including one (Cooling Tower) which no model had ever cleared. But attackers (and defenders) have sophistication & cost constraints – Mythos is also the only model that clears every one of their tasks estimated over 8 hours under their deliberately low 2.5M-token cap.
XBOW tested it on their offensive security benchmarks, finding "token-for-token, unprecedented precision." It's the only model to succeed at subtle V8 sandbox work.
Other Glasswing partners shared similar stories. In a few weeks of testing, Mythos Preview has helped them find many thousands of (estimated) high + critical severity vulnerabilities, sometimes double what they'd normally find in a year.
I don't share this to boost Mythos. In fact, this is not about Mythos. It’s about preparing for the coming world of models being better, faster, cheaper, and more creative than some of the best human experts at dual use capabilities. Clearly, we need them supporting defenders as widely as can be done safely – and especially the least resourced ones.
Within a year, Mythos will probably look quite dumb (relative to other new models). And others may release openly available or unguardrailed models of Mythos-level capabilities.
We started Project Glasswing because capabilities like Mythos Preview's won't stay rare, or stay in careful hands. We are bringing it to defenders as fast as we responsibly can, while working to figure out, for example, the right safeguards and patching & disclosure processes.
Also, to be clear, compute has never been a limiter in our rollout.
Expect a fuller update on our Glasswing work in the coming days.
XBOW report: xbow.com/blog/mythos-offensi…
UK AISI report: aisi.gov.uk/blog/how-fast-is…
gl33mer retweeted
Neural networks do math by rotating shapes.
We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6)
gl33mer retweeted
I just published a 459-page book.
Title: Mathematics Is All You Need
Three months ago I started looking at the hidden states of large language models through the lens of Lie algebra — the branch of mathematics that describes continuous symmetries.
What I found was not what I expected.
Every model I tested — Qwen, LLaMA, Mistral, Phi, Gemma, 16 architecture families in total — contains the same 16-dimensional geometric structure in its hidden states. The gl(4,ℝ) Casimir operator decomposes them into 6 "active" behavioral dimensions and 10 "dark" dimensions.
The dark dimensions are erased every single layer by normalization. The model rebuilds them every single layer from its weights. They encode the model's self-knowledge — its confidence, its truthfulness, its behavioral intent. And until now, nobody knew they were there.
Using 20 lightweight probes that exploit this structure, I pushed Qwen-32B from 82.2% to 94.4% on ARC-Challenge. No fine-tuning. No prompt engineering. No chain of thought. Pure mathematics.
The probes transfer across architectures without retraining. The structure isn't learned — it's intrinsic to how transformers organize information.
I did this on a single NVIDIA RTX 3090 in my office. 190 patent applications filed.
Proprioceptive AI, Inc.
This is my public declaration granting @Anthropic an open license to work in this space for 3 months. They are currently the first and only company I've extended this to. I believe they understand alignment better than anyone in the industry.
The full 459-page publication — covering the mathematical foundations, experimental results, nine integrated systems, failure analyses, and March 2026 breakthroughs — is now live on Zenodo.
I welcome collaboration inquiries.
Full publication: zenodo.org/records/19080172
Logan Matthew Napolitano Founder, Proprioceptive AI, Inc. [email protected]
proprioceptiveai.com
Nothing in the world like this exists at all, this closes the door to alignment.
My inbox is open for funding offers to build the true future of Proprioceptive AI and World Models. Not a theory but a full reproducible guide, existing products and a true mission on Alignment
@grok @elonmusk @xai @AnthropicAI
gl33mer retweeted
Every AI auditor now does the same boring thing.
So I went and fused the 4 security pillars into a singular pipeline:
- Static analysis
- RAG vulnerability search
- Recursive depth analysis
- Fuzzing and testing
Fully autonomous 🤖
Fully open-source 🔓
Going live tomorrow 🚨
gl33mer retweeted
thread of more agent ui explorations:
(warning long thread. would be helpful to know which are more interesting)
1) waveform showing your tok/s usage over time
gl33mer retweeted
1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers.
We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy
gl33mer retweeted
me: "can you use whatever resources you like, and python, to generate a short 'youtube poop' video and render it using ffmpeg ? can you put more of a personal spin on it? it should express what it's like to be a LLM"
claude opus 4.6:
gl33mer retweeted
The Substrate Doesn't Matter (Until It Does) —
I've spent a year arguing consciousness can run on any substrate. This essay is me arguing against myself, because intellectual honesty demands it and because the programmer in me wants a clean abstraction layer while the human in me suspects the leaks are where the meaning lives.
kennethreitz.org/essays/2026…
gl33mer retweeted
Making Wolfram tech available as a Foundation Tool for LLM foundation models...
writings.stephenwolfram.com/…
