~mechanistic
@mechanistics.bsky.social
researcher | open-source dev | sp00ky code stuff
~~lumbridge
huggingface.co/tegridydev
github.com/tegridydev
~~lumbridge
huggingface.co/tegridydev
github.com/tegridydev
Reposted by ~mechanistic
Shameless plug. I started a company and have been working hard on getting it off the ground. I would appreciate any help to boost visibility: secureorigin.io
Secure Origin
Accessible cybersecurity solutions for nonprofits and small businesses.
secureorigin.io
September 7, 2025 at 1:51 AM
Shameless plug. I started a company and have been working hard on getting it off the ground. I would appreciate any help to boost visibility: secureorigin.io
Oi, I don't post much but if you see this then you should go take a minute to check out the homie over at secureorigin.io
Good people doing good things for nonprofits and small businesses 🤙
#infosec #cybersec #security #secure #secureorigin #nonprofits
Good people doing good things for nonprofits and small businesses 🤙
#infosec #cybersec #security #secure #secureorigin #nonprofits
Secure Origin
Accessible cybersecurity solutions for nonprofits and small businesses.
secureorigin.io
September 7, 2025 at 2:53 AM
Oi, I don't post much but if you see this then you should go take a minute to check out the homie over at secureorigin.io
Good people doing good things for nonprofits and small businesses 🤙
#infosec #cybersec #security #secure #secureorigin #nonprofits
Good people doing good things for nonprofits and small businesses 🤙
#infosec #cybersec #security #secure #secureorigin #nonprofits
Reposted by ~mechanistic
hi!
I'm looking for new work opportunities
strongest areas are data analysis & threat hunting. I love SQL, regex, anomaly detection, data wrangling
experienced designing & using honeypot systems. have created novel techniques
I use python a lot, but can use whatever a situation calls for
tysm💓
I'm looking for new work opportunities
strongest areas are data analysis & threat hunting. I love SQL, regex, anomaly detection, data wrangling
experienced designing & using honeypot systems. have created novel techniques
I use python a lot, but can use whatever a situation calls for
tysm💓
August 18, 2025 at 6:45 PM
hi!
I'm looking for new work opportunities
strongest areas are data analysis & threat hunting. I love SQL, regex, anomaly detection, data wrangling
experienced designing & using honeypot systems. have created novel techniques
I use python a lot, but can use whatever a situation calls for
tysm💓
I'm looking for new work opportunities
strongest areas are data analysis & threat hunting. I love SQL, regex, anomaly detection, data wrangling
experienced designing & using honeypot systems. have created novel techniques
I use python a lot, but can use whatever a situation calls for
tysm💓
this is adorable 🥰
bakerstreetforensics.com/2025/07/20/p...
#cybersecurity #pi #raspberrypi #forensics #diy #linux #cyber #hack #opensource
bakerstreetforensics.com/2025/07/20/p...
#cybersecurity #pi #raspberrypi #forensics #diy #linux #cyber #hack #opensource
July 21, 2025 at 6:36 PM
Reposted by ~mechanistic
Attend my AI 2025 bootcamp
May 19, 2025 at 8:17 PM
Attend my AI 2025 bootcamp
Here are some of my #opensource projects & repos 🫡
#software #dev #github #code #AI #python
github.com/tegridydev
github.com/tegridydev/abstract-agent
github.com/tegridydev/python-OSINT-notebook
github.com/tegridydev/auto-md
github.com/tegridydev/open-malsec
github.com/tegridydev/mechamap
#software #dev #github #code #AI #python
github.com/tegridydev
github.com/tegridydev/abstract-agent
github.com/tegridydev/python-OSINT-notebook
github.com/tegridydev/auto-md
github.com/tegridydev/open-malsec
github.com/tegridydev/mechamap
tegridydev - Overview
Mechanistic Interpretability (MI) Research & Buildn' Cool Stuff @toolworks-dev - tegridydev
github.com
June 15, 2025 at 3:14 AM
anyone else find random code/files/projects on your drives you don't even remember doing, then you check the timestamps & see like 2:45am on a random weekday then realise you need to fix your sleep schedule? 😂
#opensource #dev #ADHD #code
#opensource #dev #ADHD #code
June 15, 2025 at 3:04 AM
anyone else find random code/files/projects on your drives you don't even remember doing, then you check the timestamps & see like 2:45am on a random weekday then realise you need to fix your sleep schedule? 😂
#opensource #dev #ADHD #code
#opensource #dev #ADHD #code
01101010 01110101 01110011 01110100 00100000 01110111 01100001 01101110 01101110 01100001 00100000 01110000 01101100 01100001 01111001 00100000 01110010 01110101 01101110 01100101 01110011 01100011 01100001 01110000 01100101 00100000 01110100 01100010 01101000
June 13, 2025 at 6:00 PM
01101010 01110101 01110011 01110100 00100000 01110111 01100001 01101110 01101110 01100001 00100000 01110000 01101100 01100001 01111001 00100000 01110010 01110101 01101110 01100101 01110011 01100011 01100001 01110000 01100101 00100000 01110100 01100010 01101000
Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files
github.com/tegridydev/a...
#opensource #LLM #AI #github #devtool #AItool #devops
github.com/tegridydev/a...
#opensource #LLM #AI #github #devtool #AItool #devops
GitHub - tegridydev/auto-md: Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files
Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files - tegridydev/auto-md
github.com
May 6, 2025 at 2:14 AM
Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files
github.com/tegridydev/a...
#opensource #LLM #AI #github #devtool #AItool #devops
github.com/tegridydev/a...
#opensource #LLM #AI #github #devtool #AItool #devops
Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts
github.com/tegridydev/a...
#AI #opensource #ollama #github #research #LLM #selfhosted #openresearch
github.com/tegridydev/a...
#AI #opensource #ollama #github #research #LLM #selfhosted #openresearch
GitHub - tegridydev/abstract-agent: Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts
Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts - tegridydev/abstract-agent
github.com
April 29, 2025 at 6:40 AM
Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts
github.com/tegridydev/a...
#AI #opensource #ollama #github #research #LLM #selfhosted #openresearch
github.com/tegridydev/a...
#AI #opensource #ollama #github #research #LLM #selfhosted #openresearch
Hydraform Self-Evolving Attention
Currently consists of a PoC research prototype for self-evolving, mutation-guided multi-headed attention.
Think of a classical Hydra, where individual heads grow, shrink or regenerate based on performance.
#AI #LLM #transformers
GitHub.com/tegridydev/hydraform
Currently consists of a PoC research prototype for self-evolving, mutation-guided multi-headed attention.
Think of a classical Hydra, where individual heads grow, shrink or regenerate based on performance.
#AI #LLM #transformers
GitHub.com/tegridydev/hydraform
GitHub - tegridydev/hydraform: Self-Evolving Python Transformer Research
Self-Evolving Python Transformer Research. Contribute to tegridydev/hydraform development by creating an account on GitHub.
GitHub.com
April 25, 2025 at 8:47 PM
Hydraform Self-Evolving Attention
Currently consists of a PoC research prototype for self-evolving, mutation-guided multi-headed attention.
Think of a classical Hydra, where individual heads grow, shrink or regenerate based on performance.
#AI #LLM #transformers
GitHub.com/tegridydev/hydraform
Currently consists of a PoC research prototype for self-evolving, mutation-guided multi-headed attention.
Think of a classical Hydra, where individual heads grow, shrink or regenerate based on performance.
#AI #LLM #transformers
GitHub.com/tegridydev/hydraform
Python based tool that generates synthetic RF IQ recordings + optional steganographic payloads embedded via LSB
github.com/tegridydev/r...
#cybersec #opensource #data
github.com/tegridydev/r...
#cybersec #opensource #data
GitHub - tegridydev/rf-stego-dataset: Python based tool that generates synthetic RF IQ recordings + optional steganographic payloads embedded via LSB
Python based tool that generates synthetic RF IQ recordings + optional steganographic payloads embedded via LSB - tegridydev/rf-stego-dataset
github.com
April 24, 2025 at 9:45 PM
Python based tool that generates synthetic RF IQ recordings + optional steganographic payloads embedded via LSB
github.com/tegridydev/r...
#cybersec #opensource #data
github.com/tegridydev/r...
#cybersec #opensource #data
Reposted by ~mechanistic
Python OSINT Notebook
- Core Tools & Libraries
- Installation & Configuration
- Using OSINT Tools via CLI
- Python Scripting with OSINT Libraries
- Combining Tools in a Script
- OSINT Data Integration
and more.
github.com/tegridydev/p...
Contributor @mechanistics.bsky.social
- Core Tools & Libraries
- Installation & Configuration
- Using OSINT Tools via CLI
- Python Scripting with OSINT Libraries
- Combining Tools in a Script
- OSINT Data Integration
and more.
github.com/tegridydev/p...
Contributor @mechanistics.bsky.social
April 24, 2025 at 4:32 PM
Python OSINT Notebook
- Core Tools & Libraries
- Installation & Configuration
- Using OSINT Tools via CLI
- Python Scripting with OSINT Libraries
- Combining Tools in a Script
- OSINT Data Integration
and more.
github.com/tegridydev/p...
Contributor @mechanistics.bsky.social
- Core Tools & Libraries
- Installation & Configuration
- Using OSINT Tools via CLI
- Python Scripting with OSINT Libraries
- Combining Tools in a Script
- OSINT Data Integration
and more.
github.com/tegridydev/p...
Contributor @mechanistics.bsky.social
Open Source AI Agents | Github/Repo List | [2025]
huggingface.co/blog/tegridy...
(using it as my own notepad & decided i might keep it up to date if i post it here, instead of making the 15th_version of it and not saving it with a name i can remember on my desktop lol)
#ai #aiagents #opensource
huggingface.co/blog/tegridy...
(using it as my own notepad & decided i might keep it up to date if i post it here, instead of making the 15th_version of it and not saving it with a name i can remember on my desktop lol)
#ai #aiagents #opensource
February 21, 2025 at 7:19 PM
Open Source AI Agents | Github/Repo List | [2025]
huggingface.co/blog/tegridy...
(using it as my own notepad & decided i might keep it up to date if i post it here, instead of making the 15th_version of it and not saving it with a name i can remember on my desktop lol)
#ai #aiagents #opensource
huggingface.co/blog/tegridy...
(using it as my own notepad & decided i might keep it up to date if i post it here, instead of making the 15th_version of it and not saving it with a name i can remember on my desktop lol)
#ai #aiagents #opensource
WTF is Fine-Tuning? (intro4devs)
Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? 😃
Here's a cheat sheet for devs (but open to anyone!)
#llm #finetune #ai
---
huggingface.co/blog/tegridy...
Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? 😃
Here's a cheat sheet for devs (but open to anyone!)
#llm #finetune #ai
---
huggingface.co/blog/tegridy...
WTF is Fine-Tuning? (intro4devs) | [2025]
A Blog post by GO:OD:AM on Hugging Face
huggingface.co
February 17, 2025 at 9:46 AM
WTF is Fine-Tuning? (intro4devs)
Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? 😃
Here's a cheat sheet for devs (but open to anyone!)
#llm #finetune #ai
---
huggingface.co/blog/tegridy...
Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? 😃
Here's a cheat sheet for devs (but open to anyone!)
#llm #finetune #ai
---
huggingface.co/blog/tegridy...
Just uploaded Open-MalSec v0.1 samples, an early-stage dataset for phishing, scams, and malware-related training etc
Open to feedback & contributions—more updates coming soon! 🫡
🔗 huggingface.co/datasets/tegridydev/open-malsec
#cybersecurity #threatintel #opensource #huggingface #dataset #llm
Open to feedback & contributions—more updates coming soon! 🫡
🔗 huggingface.co/datasets/tegridydev/open-malsec
#cybersecurity #threatintel #opensource #huggingface #dataset #llm
tegridydev/open-malsec · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 31, 2025 at 6:57 AM
Just uploaded Open-MalSec v0.1 samples, an early-stage dataset for phishing, scams, and malware-related training etc
Open to feedback & contributions—more updates coming soon! 🫡
🔗 huggingface.co/datasets/tegridydev/open-malsec
#cybersecurity #threatintel #opensource #huggingface #dataset #llm
Open to feedback & contributions—more updates coming soon! 🫡
🔗 huggingface.co/datasets/tegridydev/open-malsec
#cybersecurity #threatintel #opensource #huggingface #dataset #llm
building out a prototype python tool to generate synthetic stepped perspective reasoning datasets🦿
#ollama #python #opensource #reasoning #datasets #huggingface
#ollama #python #opensource #reasoning #datasets #huggingface
January 30, 2025 at 10:58 PM
building out a prototype python tool to generate synthetic stepped perspective reasoning datasets🦿
#ollama #python #opensource #reasoning #datasets #huggingface
#ollama #python #opensource #reasoning #datasets #huggingface
Reposted by ~mechanistic
This is an interesting finding: people who use AI a lot can identify when AI has been used by others.
So, if you're a college professor, time to start really playing with these models.
So, if you're a college professor, time to start really playing with these models.
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
In this paper, we study how well humans can detect text generated by commercial LLMs (GPT-4o, Claude, o1). We hire annotators to read 300 non-fiction English articles, label them as either…
buff.ly
January 29, 2025 at 11:44 PM
This is an interesting finding: people who use AI a lot can identify when AI has been used by others.
So, if you're a college professor, time to start really playing with these models.
So, if you're a college professor, time to start really playing with these models.
So, what is #MechanisticInterpretability 🤔
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours...
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours...
January 29, 2025 at 9:26 PM
So, what is #MechanisticInterpretability 🤔
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours...
Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours...
I’ve been working on something I call the Mixture of Perspectives (MoP) framework — Picture an internal roundtable: each “perspective” has its own values, priorities, or reasoning style (kind of like how philosophers all disagree yet somehow coexist).
github.com/tegridydev/m...
github.com/tegridydev/m...
GitHub - tegridydev/mixture-of-persona-research: A “Mixture of Perspectives” Framework for Ethical AI
A “Mixture of Perspectives” Framework for Ethical AI - tegridydev/mixture-of-persona-research
github.com
January 29, 2025 at 9:17 PM
I’ve been working on something I call the Mixture of Perspectives (MoP) framework — Picture an internal roundtable: each “perspective” has its own values, priorities, or reasoning style (kind of like how philosophers all disagree yet somehow coexist).
github.com/tegridydev/m...
github.com/tegridydev/m...
