AI/ML

R1+Sonnet has set a new SOTA on the aider polyglot benchmark. At 14X less cost compared to o1.

aider is AI pair programming in your terminal. Contribute to Aider-AI/aider development by creating an account on GitHub.

I’m a big fan of Claude Sonnet. I’m ashamed to admit, it’s mostly vibes based. It’s friendlier and writes code in a way that I like. The…

Quantitative benchmarks of LLM code editing skill.

Results from Wolfram's ongoing tracking of LLM performance. The benchmark is based on a Wolfram Language code generation task.

Kagi Search Help

In this video, I look at olmOCR, the OpenOCR system from Allen AI. Colab: https://dripl.ink/HpaK4 Blog: https://olmocr.allenai.org/blog macOS ver: https://jonathansoma.com/words/olmocr-on-macos-with-lm-studio.html For more tutorials on using LLMs and building agents, check out my Patreon Patreon: https://www.patreon.com/SamWitteveen Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨‍💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:31 Allen AI Blog 01:20 olmOCR Blog 02:08 olmOCR Hugging Face 04:52 olmOCR GitHub 05:41 Demo 05:59 Running olmOCR on macOS with LM Studio

Learn how to have your own locally hostedl OpenAI Deep Research-like service in Msty

LLM 0.23 is out today, and the signature feature is support for schemas—a new way of providing structured output from a model that matches a specification provided by the user. …

For some time, I’ve argued that a common conception of AI is misguided. This is the idea that AI systems like large language and vision models are individual intelligent agents, analogous to human agents. Instead, I’ve argued that these models are “cultural technologies” like writing, print, pictures, libraries, internet search engines, and Wikipedia.

Hello and welcome to my new blog post. Today I am going to discuss a future threat which is invisible. With greater power comes greater…

Converts ASCII Prompts to Unicode Generating “Invisible” Prompts - Unighost_Prompt_Injection.py

Learn about invisible prompt injection, which is a silent threat to secure AI.

Payloads All The Things, a list of useful payloads and bypasses for Web Application Security

I tested my local, small LLM connected to my Zotero database in Open WebUI against NotebookLM. The results were really, truly surprising. Please Like and Subscribe to support the channel! @LearnMetaAnalysis I tested Granite 3.1-2b and Granite 3.1-8b vs NotebookLM. I am now more impressed than ever! If you find Granite hallucinating with the default temperature setting, I've had good results setting it at about .20. Results from the testing: https://docs.google.com/spreadsheets/d/1nW7B_A7fzayaMancYwU89ApOOfLG5WOefzstdL_fg-Y/edit?usp=sharing Learn how to set up your own local, private research assistant like Dwayne with no coding: https://youtu.be/b2BSZfOtD_w The original RAG template I adapted (my modified version is in the google sheet): https://medium.com/@kelvincampelo/how-ive-optimized-document-interactions-with-open-webui-and-rag-a-comprehensive-guide-65d1221729eb Tutorials and how-to guides: Connect a LLM to your Zotero (or any other local folder): https://youtu.be/b2BSZfOtD_w Conventional meta-analysis: https://www.youtube.com/playlist?list=PLXa5cTEormkEbYpBIgikgE0y9QR7QIgzs Three-level meta-analysis: https://www.youtube.com/playlist?list=PLXa5cTEormkHwRmu_TJXa7fSb6-WBXXoJ Three-level meta-analysis with correlated and hierarchical effects and robust variance estimation: https://www.youtube.com/playlist?list=PLXa5cTEormkEGenfcnp9X5dQUhmm7f9Jp Want free point and click (no coding required) meta-analysis software? Check out Simple Meta-Analysis: https://learnmeta-analysis.com/pages/simple-meta-analysis-software Tired of manually extracting data for systematic review and meta-analysis? Check out AI-Assisted Data Extraction, a free package for R! https://youtu.be/HuWXbe7hgFc Free ebook on meta-analysis in R (no download required): https://noah-schroeder.github.io/reviewbook/ Visit our website at https://learnmeta-analysis.com/ 0:40 Setup 4:05 Results

Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection...

Comparison and ranking the performance of over 30 AI models (LLMs) across key metrics including quality, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others.

Discover amazing ML apps made by the community

Learn how to make simple changes that help your LLM chat with Zotero like a pro! I’m getting well written, well-cited results from a 2b parameter LLM. Please Like and Subscribe to support the channel! @LearnMetaAnalysis Embedding result testing: https://docs.google.com/spreadsheets/d/1P3rOLEO_NtCUYxaFIVaVZfMv4BOkQb3w/edit?usp=sharing&ouid=111617079417577058774&rtpof=true&sd=true Granite 3.1 Dense is my favorite LLM for this setup right now, it's available in 2b and 8b versions for ollama - https://ollama.com/library/granite3.1-dense:2b Snowflake Arctic Embed 2 has performed well for me so far as an embedding model: https://ollama.com/library/snowflake-arctic-embed2 MTEB leaderboard to see what embedding models perform well at different tasks: https://huggingface.co/spaces/mteb/leaderboard How to connect a LLM to Zotero - https://youtu.be/b2BSZfOtD_w I generally prefer local, private LLMs, but if you need large SOTA models like ChatGPT, Claude, Deepseek, Gemini, or Grok, check out ChatLLM - My 3 month review of ChatLLM: https://youtu.be/_Z3nLKvTbGc Tutorials and how-to guides: Conventional meta-analysis: https://www.youtube.com/playlist?list=PLXa5cTEormkEbYpBIgikgE0y9QR7QIgzs Three-level meta-analysis: https://www.youtube.com/playlist?list=PLXa5cTEormkHwRmu_TJXa7fSb6-WBXXoJ Three-level meta-analysis with correlated and hierarchical effects and robust variance estimation: https://www.youtube.com/playlist?list=PLXa5cTEormkEGenfcnp9X5dQUhmm7f9Jp Want free point and click (no coding required) meta-analysis software? Check out Simple Meta-Analysis: https://learnmeta-analysis.com/pages/simple-meta-analysis-software Tired of manually extracting data for systematic review and meta-analysis? Check out AI-Assisted Data Extraction, a free package for R! https://youtu.be/HuWXbe7hgFc Free ebook on meta-analysis in R (no download required): https://noah-schroeder.github.io/reviewbook/ Visit our website at https://learnmeta-analysis.com/ 0:15 Knowledge 0:59 Help make this better 1:32 Modify ‘knowledge’ settings 5:46 Demo of results 7:22 Top K 11:25 Testing Different embeddings 13:25 Use # not models 14:45 Impatient people (like me!) start here 21:38 Example Results

Contribute to simonw/nicar-2025-scraping development by creating an account on GitHub.

OpenAI are rolling out their Deep research "agentic" research tool to their $20/month ChatGPT Plus users today, who get 10 queries a month. $200/month ChatGPT Pro gets 120 uses. Deep …

GitHub Gist: instantly share code, notes, and snippets.

The latest reasoning model and what it says about the direction of inference time compute and RL training.

There were a number of announcements at GitHub Universe that impacted VS Code and Copilot users. This is a roundup of those announcements, including the much-anticipated Copilot Edits, Intent Detection, Model Selection, and Code Reviews. We'll also take a look at some of the amazing extensions created by the VS Code team, including using images for prompts with Vision for Copilot, analyzing CSV data with Data Analysis for Copilot, and GitHub Pull Requests. 🔎 Chapters: 00:00 GitHub Universe announcements 00:30 Demo - Copilot Edits 05:30 Demo - Intent Detection 09:06 Demo - Data Analysis for Copilot 10:19 Demo - GitHub Pull Requests Copilot Integration 13:10 Happy Coding 🔗 Links: https://aka.ms/get-copilot https://aka.ms/IntroducingCopilotEdits Featuring: Rob Conery #vscode #copilot #githubcopilot

Is AI progress slowing down? This piece by Arvind Narayanan and Sayash Kapoor is the single most insightful essay about AI and LLMs I've seen in a long time.

Redefining small LMs performance In this project, we develop technologies for creating, improving, and specializing small LMs (~10B parameters or less). Our research involves self-improvement strategies, feedback-driven teaching methods between large and small models and utilizing domain specific data to specialize LMs. We focus on using richer training signals for teaching small LMs to do […]

Kobra is A Visual Programming language for ML

Get scalable SQL to modernize applications on any cloud, offload expensive databases, and create and extend modern applications with ML/AI.

Artificial Intelligence and Machine Learning - Free source code and tutorials for Software developers and Architects.; Updated: 9 Jan 2021