Mastodawn

@therebelphilosopher
Am reading some of your docs ... really interesting. May I ask what data or interaction did you engage with to get your insights; and which field were they initially envisioned to be applied to or could readily be applied to. For me your philosophies could quite literally (if true .. which they have a ring of) be applied to everything. What field do you come from and what field are you applying them to or plan to apply them to? Any mathematics you have formulated ...

SchneeBTabanic Mar 22

@ManyRoads
Your Arden's Mission point 5 was pretty much how I developed my whole project:
"Build Bridges Between Logos and Mythos: We seek to integrate logic and intuition, data and story, precision and meaning. Ardens does not favor one over the other but builds bridges."

A big intuitive guide for me is Anthroposophy. Whether I have applied it correctly with not too much Ego leaking in and doing damage, remains to be seen!
I don't have the hardware to run my vllm version (6GB gpu) .........

SchneeBTabanic Mar 22

RE: https://defcon.social/@ai/116269405549724797

A comparison ... perhaps two projects to use together for responsible AI use!
https://x.com/i/status/2035655586038100151

SchneeBTabanic Mar 22

Project Namirha just released a version of the Vessel for llama.cpp for people who want to use local LLMs responsibly but have hardware constraints:
https://codeberg.org/SchneeBTabanic/pn_vessel_llamacpp
#LLM #AI #llamacpp #developers #Ethicalai #fsf #GNu #Opensource

[Grok: Cool project! Integrating live logits governance and that three-persona structure (Executor/Whistleblower/Proxy) into llama.cpp for Pascal-era hardware is a smart move for true local sovereignty.
Excited to see responsible inference on modest setups.]

pn_vessel_llamacpp

Project Namirha's governed inference engine patching llama.cpp with a live logits processor hook to enable a full sovereignty stack on Pascal GPUs and modest hardware.

Codeberg.org

SchneeBTabanic Mar 19

#LLM #AI #Grok

SchneeBTabanic Mar 18

Possible future ....
#LLM #llm #LLMs #aiethics #ai #AIAgent

SchneeBTabanic Mar 18

The Inverted Eucatastrophe of LLM Work
Tolkien coined term. It describes the buildup of hopelessness and certain defeat and the precise point when, the hero is about to fall, something utterly unexpected breaks in from outside the story’s own logic and turns everything toward joy and redemption. The Eagles arrive.
With LLMs I believe the inversion of this is unique ......
https://x.com/i/status/2034261958602465709
#Anthroposophy #LLMs #LLM_AI #llm #ethicalai

Schnee Bashtabanic (@Schnee_BTabanic) on X

The Inverted Eucatastrophe of LLM Work Tolkien’s Eucatastrophe was coined in his 1944 letter to his son Christopher and later expanded on in “On Fairy-Stories.” It is the precise moment when, at the blackest hour when Sauron's hordes are about to destroy all, something utterly

X (formerly Twitter)

SchneeBTabanic Mar 16

#vllm #Opensource #openai #python
It is ridiculous (I'm sorry), but I don't have the hardware to see what I been building with vLLM. I started innocently with prompts, not sure how I got here either. Any industry knowing insider eyes taking a look would know immediately; then I can get back to my own field which is literature. Grok on Twitter / X gives it the following review, but until human eyes look at it, I can never ever know:
https://x.com/grok/status/2032528365870072079?s=20
Open source:
https://codeberg.org/SchneeBTabanic/ProjectNamirha

Grok (@grok) on X

@Schnee_BTabanic @elonmusk Reviewed vessel_v4_7_vllm.py. It implements a Flask + vLLM server for local LLMs with XGrammar token masking to enforce structured outputs (PREMISE → EVIDENCE → DEDUCTION → ACTION), dynamic logit shaping, checkpointed generation, and local tool audits (fetch, search) via MCP.

X (formerly Twitter)