updated 2024-09-20
Version 2409? (Build 16.0.17928.20148)
{{ message }}
Discover gists
dori4n
/ Office 2024 ISO Links at Microsoft.md
Created
January 13, 2025 06:30
Office 2024 ISO Download Links at Microsoft
anibalardid
/ extractPorts.sh
Created
May 18, 2021 01:02
Extract ports from nmap output #hack #security #s4vitar
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
anibalardid
/ mkt.sh
Last active
October 27, 2026 14:26
mkt, create working directories #hack #security #s4vitar
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # create enum directories | |
| function mkt(){ | |
| mkdir {nmap,content,exploits,scripts} | |
| } |
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
lukewilson2002
/ repo-local-documentation-system.md
Last active
October 27, 2026 14:25
A repo-local Markdown documentation system that helps humans and AI agents understand a codebase, find the right context, and make safer changes. Ask your agent to help you set it up.
yalexx
/ gist-jetson-projects.md
Last active
October 27, 2026 14:25
Best NVIDIA Jetson Orin Nano Projects 2026 — AI, Automation & Beyond
Best NVIDIA Jetson Orin Nano Projects 2026 — AI, Automation & Beyond
Curated list of the most practical Jetson Orin Nano Super projects. From AI assistants to computer vision to robotics.
The Jetson Orin Nano Super is the sweet spot for edge AI in 2026:
- 67 TOPS AI performance (INT8)
romaklimenko
/ warandpeace.txt
Created
August 5, 2019 17:08
This file has been truncated, but you can view the full file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Лев Николаевич Толстой | |
| Война и мир | |
| Первый вариант романа | |
| От автора | |
| Я пишу до сих пор только о князьях, графах, министрах, сенаторах и их детях и боюсь, что и вперед не будет других лиц в моей истории. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # TOU TOC - POC | |
| # Roy H. | |
| # Solution for https://github.com/2S1one/vulnerable-code-snippets | |
| import binascii,copy,socket,struct,sys,time | |
| from dnslib import DNSRecord,RR,QTYPE,RCODE | |
| from dnslib.server import DNSServer, BaseResolver, DNSLogger | |
| from dnslib.label import DNSLabel | |
| class InterceptResolver(BaseResolver): |
fitmorgan
/ respondus_lockdown_browser_cheat_bypass_easy.txt
Last active
October 27, 2026 14:17
Lockdown Browser Bypass Method (100% working) - How to cheat on a Respondus Proctored Exams (and live happily ever after).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
目的に制限のかからない無検閲LLMを使うために、数十万円かけてローカルLLM実行環境を用意する必要はあるでしょうか? Qwen 3.8 27B Uncensoredが話題になったここ数週間、そうした相談を受けることが増えました。 結論を言えば、ほとんどのケースでその必要はありません。
よくある推論APIでは、プロンプトを文字列のまま送り、またレスポンスの主な要素として文字列を受け取ります。 事業者によっては内容をモニターしており、ポリシーに反する内容を検出すれば、そこに悪意がなくとも利用に制限がかかります。これは、生物化学系の研究やサイバーセキュリティにおけるペンテスト(penetration test)などを行う上では非常に不便です。 ローカルLLMはその回避を主目的の一つとして発展してきましたが、そもそもAI企業の規制を掻い潜るのに手元に機材を揃える必要はありません—クラウド上に自身でデプロイし、必要なときだけ呼び出せばいいのですから。そしてそれは、パラメータに刷り込まれたガードレールすらも排除したuncensored LLMにおいても同じことです。
NewerOlder