Akshay 🚀's banner

Akshay 🚀

@akshay_pachaar • 281,738 subscribers

Simplifying LLMs, AI Agents, RAG, and Machine Learning for you! • Co-founder @dailydoseofds_• BITS Pilani • 3 Patents • ex-AI Engineer @ LightningAI

Shorts

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

243,333 views

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

255,129 views

Real-time object detection will never be the same. Traditional YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model:

Real-time object detection will never be the same. Traditional YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model:

374,108 views

Hermes meets SuperGrok! xAI just made every SuperGrok subscription work inside Hermes Agent. One browser login, no API key, no separate billing. And it doesn't just unlock text chat with Grok 4.3. The same OAuth token gives the agent access to: → Grok Text-to-Speech for spoken responses → Grok Imagine for image and video generation → x_search for real-time X/Twitter search I just added a new X Research Agent profile to my Hermes. Now my agent watches X while I ship. Setup takes about 60 seconds: Available on every SuperGrok tier, no restrictions. I wrote a full deep dive covering Hermes agent's architecture, memory system, self-evolving skills, GEPA optimization, and setting up multiple specialized agents The article is quoted below.

143,942 views

Microsoft just changed the game! 🔥 They've open-sourced bitnet.cpp: a blazing-fast 1-bit LLM inference framework that runs directly on CPUs. Why is this a game-changer❓ You can now run 100B parameter models on local devices with up to 6x speed improvements and 82% less energy consumption—all without a GPU! The future we've been waiting for: fast, efficient, and private AI that works anytime, anywhere.✨ The model is also available on HuggingFace, you can try it right away! I've shared Link to the GitHub repo in next tweet, where you'll find all the details. _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on AI and Machine Learning!

Sensitive content

Microsoft just changed the game! 🔥 They've open-sourced bitnet.cpp: a blazing-fast 1-bit LLM inference framework that runs directly on CPUs. Why is this a game-changer❓ You can now run 100B parameter models on local devices with up to 6x speed improvements and 82% less energy consumption—all without a GPU! The future we've been waiting for: fast, efficient, and private AI that works anytime, anywhere.✨ The model is also available on HuggingFace, you can try it right away! I've shared Link to the GitHub repo in next tweet, where you'll find all the details. _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on AI and Machine Learning!

511,729 views

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

215,344 views

Neural network visualized!

Neural network visualized!

571,609 views

Drag-and-drop UI to build AI agents! Langflow is a powerful visual tool for building and deploying AI-powered agents and workflows—without writing any code. Supports all major LLMs, vector DBs, etc. 100% open-source, 62k+ stars 🌟

Drag-and-drop UI to build AI agents! Langflow is a powerful visual tool for building and deploying AI-powered agents and workflows—without writing any code. Supports all major LLMs, vector DBs, etc. 100% open-source, 62k+ stars 🌟

208,002 views

AI agents can finally talk to your frontend! The AG-UI Protocol bridges the critical gap between AI agents and frontend apps, making human-agent collaboration seamless. MCP: Agents to tools A2A: Agents to agents AG-UI: Agents to users 100% open-source.

AI agents can finally talk to your frontend! The AG-UI Protocol bridges the critical gap between AI agents and frontend apps, making human-agent collaboration seamless. MCP: Agents to tools A2A: Agents to agents AG-UI: Agents to users 100% open-source.

188,893 views

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

126,122 views

Google released Gemma 3 270M, a new model for hyper-efficient local AI! We'll fine-tune this model and make it very smart at playing chess and predict the next move. Tech stack: - Unsloth AI for efficient fine-tuning. - Hugging Face transformers to run it locally. Let's go! 🚀

Google released Gemma 3 270M, a new model for hyper-efficient local AI! We'll fine-tune this model and make it very smart at playing chess and predict the next move. Tech stack: - Unsloth AI for efficient fine-tuning. - Hugging Face transformers to run it locally. Let's go! 🚀

145,644 views

Google just open-sourced LangExtract Python library! It uses LLMs to extract entities, attributes, and relations—with exact source grounding—from unstructured documents. Flexible LLM support (Gemini, OpenAI, Ollama) 100% open-source.

Google just open-sourced LangExtract Python library! It uses LLMs to extract entities, attributes, and relations—with exact source grounding—from unstructured documents. Flexible LLM support (Gemini, OpenAI, Ollama) 100% open-source.

120,405 views

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

52,426 views

K-Means is simple. Making it fast on GPU isn't. Flash-KMeans is an IO-aware implementation of exact k-means that rethinks the algorithm around modern GPU bottlenecks. By attacking the memory bottlenecks directly, Flash-KMeans achieves: - 30x speedup over cuML - 200x speedup over FAISS Using the same exact algorithm, just engineered for today’s hardware. At the million-scale, Flash-KMeans can complete a k-means iteration in milliseconds. Here's why this matters today: K-means has always been an offline primitive. Something you run once to preprocess data and move on. These speedups change that. ↳ Vector databases like FAISS use k-means to build search indices. Faster k-means means you can re-index dynamically as data changes, not batch it overnight. ↳ LLM quantization methods need k-means to find optimal weight codebooks, per layer, repeatedly. What takes hours could now take minutes. ↳ MoE models need fast token routing at inference time. Millisecond k-means makes it viable to run this inside the inference loop, not just in preprocessing. The 200x over FAISS is the number to internalize. FAISS is the industry standard. Most production vector search systems sit on top of it. Link to the paper and code in next tweet!

K-Means is simple. Making it fast on GPU isn't. Flash-KMeans is an IO-aware implementation of exact k-means that rethinks the algorithm around modern GPU bottlenecks. By attacking the memory bottlenecks directly, Flash-KMeans achieves: - 30x speedup over cuML - 200x speedup over FAISS Using the same exact algorithm, just engineered for today’s hardware. At the million-scale, Flash-KMeans can complete a k-means iteration in milliseconds. Here's why this matters today: K-means has always been an offline primitive. Something you run once to preprocess data and move on. These speedups change that. ↳ Vector databases like FAISS use k-means to build search indices. Faster k-means means you can re-index dynamically as data changes, not batch it overnight. ↳ LLM quantization methods need k-means to find optimal weight codebooks, per layer, repeatedly. What takes hours could now take minutes. ↳ MoE models need fast token routing at inference time. Millisecond k-means makes it viable to run this inside the inference loop, not just in preprocessing. The 200x over FAISS is the number to internalize. FAISS is the industry standard. Most production vector search systems sit on top of it. Link to the paper and code in next tweet!

36,317 views

Transformers & LLMs cheatsheets for Stanford's CME-295! Covering tokenization, self-attention, prompting, fine-tuning, LLM-as-a-judge, RAG, AI Agents, and reasoning models. 100% free and open-source.

Transformers & LLMs cheatsheets for Stanford's CME-295! Covering tokenization, self-attention, prompting, fine-tuning, LLM-as-a-judge, RAG, AI Agents, and reasoning models. 100% free and open-source.

101,598 views

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

58,152 views

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

31,249 views

Check this!! Now you can scrape ANY website by just writing a prompt. Using 's /extract endpoint, just describe what you want to extract in a prompt. This produces LLM-ready structured output. No more hard coding!

Check this!! Now you can scrape ANY website by just writing a prompt. Using 's /extract endpoint, just describe what you want to extract in a prompt. This produces LLM-ready structured output. No more hard coding!

64,158 views

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇

73,967 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

937,884 views • 28 days ago

How to build a 1-person AI company that: - Runs locally - 100% open-source - No human employees, all agents - Real-time collaboration via email Multi-agent orchestration is not new. Plenty of frameworks already let agents hand off tasks, run in parallel, and talk to each other. So the interesting question is not whether agents can collaborate. It is what structure you use to make them collaborate. The common approach is to wire a graph of nodes and edges and reason about the plumbing yourself. It works, but you are learning a new abstraction just to describe who does what. There is a coordination structure we have trusted for a hundred years already: an organization. Every company runs the same way. People have roles, roles have reporting lines, and work moves up and down that chart without anyone relaying each message by hand. Map that onto agents and the whole thing gets intuitive. You lay out an org chart, each agent fills one role, you talk to the person at the top, and the org sorts out the work between them. You already know how a company works, so you already know how to run one here. There is no new abstraction to learn. That is exactly what Alook does. Each agent is a live Claude Code or OpenCode session with a defined role, a reporting line, and its own email inbox. The agents coordinate over email, the same way a team would. And it all runs locally through a runtime on your own machine, so nothing leaves your setup. You bring your own agent too. Claude Code and Codex both work, and if you would rather stay fully open source and local, OpenCode works the same way. To show how this feels in practice, I set up three agents as a small sales team. Vi is the one I talk to. I hand Vi a goal, and Vi routes the work down the chart. Neile runs prospect research. Vi passes the target criteria, and Neile reports back a ranked list of names, roles, and companies, each with a suggested angle and a confidence score. Lliane runs outreach. Vi hands over the messaging angle and follow-up cadence, and Lliane reports back on emails sent, responses received, and any deal that needs escalation. I never relay a message between them. Neile and Lliane report to Vi, and Vi updates me in one place. The whole thing is open source and self-hosted, so it runs on your machine with your own agents. Give the repo a star if you want to follow where it goes: I also wrote a full walkthrough on building your own AI company with it, from a blank org chart to a running job. The article is quoted below. Cheers! :)

How to build a 1-person AI company that: - Runs locally - 100% open-source - No human employees, all agents - Real-time collaboration via email Multi-agent orchestration is not new. Plenty of frameworks already let agents hand off tasks, run in parallel, and talk to each other. So the interesting question is not whether agents can collaborate. It is what structure you use to make them collaborate. The common approach is to wire a graph of nodes and edges and reason about the plumbing yourself. It works, but you are learning a new abstraction just to describe who does what. There is a coordination structure we have trusted for a hundred years already: an organization. Every company runs the same way. People have roles, roles have reporting lines, and work moves up and down that chart without anyone relaying each message by hand. Map that onto agents and the whole thing gets intuitive. You lay out an org chart, each agent fills one role, you talk to the person at the top, and the org sorts out the work between them. You already know how a company works, so you already know how to run one here. There is no new abstraction to learn. That is exactly what Alook does. Each agent is a live Claude Code or OpenCode session with a defined role, a reporting line, and its own email inbox. The agents coordinate over email, the same way a team would. And it all runs locally through a runtime on your own machine, so nothing leaves your setup. You bring your own agent too. Claude Code and Codex both work, and if you would rather stay fully open source and local, OpenCode works the same way. To show how this feels in practice, I set up three agents as a small sales team. Vi is the one I talk to. I hand Vi a goal, and Vi routes the work down the chart. Neile runs prospect research. Vi passes the target criteria, and Neile reports back a ranked list of names, roles, and companies, each with a suggested angle and a confidence score. Lliane runs outreach. Vi hands over the messaging angle and follow-up cadence, and Lliane reports back on emails sent, responses received, and any deal that needs escalation. I never relay a message between them. Neile and Lliane report to Vi, and Vi updates me in one place. The whole thing is open source and self-hosted, so it runs on your machine with your own agents. Give the repo a star if you want to follow where it goes: I also wrote a full walkthrough on building your own AI company with it, from a blank org chart to a running job. The article is quoted below. Cheers! :)

166,723 views • 13 days ago

Andrej Karpathy said: "There's room for an incredible new product in the second brain space" This might be it. (bookmark it) Everyone is suddenly building a second brain. Karpathy's LLM wiki pattern went viral, and half of X is now hand-wiring Obsidian to Claude Code so an agent maintains their notes for them. The idea is beautiful: stop making your AI re-read raw notes on every question. Let it build a wiki that compounds. As Karpathy put it, "LLMs don't get bored, they don't forget to update a cross-reference (backlinks), and can touch 15 files in one pass." But if you start doing it manually, it becomes a project in itself. You wire up the vault, the agents, the schedules, the integrations, and then you babysit all of it. So I sat down with Arjun, who actually built the open source version of this, and we broke down what it looks like when the whole thing already works out of the box. It just crossed 15K stars on GitHub. Think Claude's desktop app, open source, with two things layered on top: → A work brain: background agents index your emails, meetings, and notes into a living knowledge graph that updates itself as you work. → Work surfaces: chat is not the best interface for real work, so you get an email client, a meeting note taker, a browser, and a code mode where you and the AI actually collaborate. The part that got me: a customer email comes in asking for a product change, a background agent triages it, spins up Claude Code in its own worktree, and the feature is written before you are back at your desk. Bring your existing Obsidian vault, connect Slack, X, and Fireflies, and let it run your day. Here's the full breakdown of what we covered in this session: Enjoy! 00:00 Intro 01:08 What is Roboat (an open source AI co-worker) 02:42 The second brain (a knowledge graph of your work) 04:01 Bringing your existing Obsidian vault in 04:46 Work surfaces 05:29 Meetings and automatic note taking 06:53 Connecting Slack, X and other sources 07:55 Background agents that run your day 09:24 Code mode (Claude Code and Codex) 10:18 Demo: from an email to written code 14:28 Guardrails: approvals and agent workspaces 17:15 Scheduling agents on a cron 18:52 The browser work surface (browser use) 20:42 Wrapping up: automating your whole day 22:44 Outro Checkout Rowboat's GitHub repo: (don't forget to star 🌟) My co-founder recently wrote a great article on the same idea, and I highly recommend reading it as well. The article is quoted below. Here's my session with Arjun:

Andrej Karpathy said: "There's room for an incredible new product in the second brain space" This might be it. (bookmark it) Everyone is suddenly building a second brain. Karpathy's LLM wiki pattern went viral, and half of X is now hand-wiring Obsidian to Claude Code so an agent maintains their notes for them. The idea is beautiful: stop making your AI re-read raw notes on every question. Let it build a wiki that compounds. As Karpathy put it, "LLMs don't get bored, they don't forget to update a cross-reference (backlinks), and can touch 15 files in one pass." But if you start doing it manually, it becomes a project in itself. You wire up the vault, the agents, the schedules, the integrations, and then you babysit all of it. So I sat down with Arjun, who actually built the open source version of this, and we broke down what it looks like when the whole thing already works out of the box. It just crossed 15K stars on GitHub. Think Claude's desktop app, open source, with two things layered on top: → A work brain: background agents index your emails, meetings, and notes into a living knowledge graph that updates itself as you work. → Work surfaces: chat is not the best interface for real work, so you get an email client, a meeting note taker, a browser, and a code mode where you and the AI actually collaborate. The part that got me: a customer email comes in asking for a product change, a background agent triages it, spins up Claude Code in its own worktree, and the feature is written before you are back at your desk. Bring your existing Obsidian vault, connect Slack, X, and Fireflies, and let it run your day. Here's the full breakdown of what we covered in this session: Enjoy! 00:00 Intro 01:08 What is Roboat (an open source AI co-worker) 02:42 The second brain (a knowledge graph of your work) 04:01 Bringing your existing Obsidian vault in 04:46 Work surfaces 05:29 Meetings and automatic note taking 06:53 Connecting Slack, X and other sources 07:55 Background agents that run your day 09:24 Code mode (Claude Code and Codex) 10:18 Demo: from an email to written code 14:28 Guardrails: approvals and agent workspaces 17:15 Scheduling agents on a cron 18:52 The browser work surface (browser use) 20:42 Wrapping up: automating your whole day 22:44 Outro Checkout Rowboat's GitHub repo: (don't forget to star 🌟) My co-founder recently wrote a great article on the same idea, and I highly recommend reading it as well. The article is quoted below. Here's my session with Arjun:

45,585 views • 10 days ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

118,124 views • 1 month ago

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

468,265 views • 6 months ago

The Hermes Desktop App is insanely good. It's now the best way to run AI agents on your computer. Here's the full setup, start to finish. Enjoy! Chapters: 00:00 - why Hermes desktop is a game changer 00:46 - downloading and installing the desktop app 01:47 - picking your model and provider 02:52 - sessions, settings, and gateway connection 04:08 - adding a custom MCP server 04:58 - memory and context (the three-tier system) 06:52 - connecting to Telegram 09:45 - skills and tools 11:06 - the skills hub (built-in and community skills) 11:50 - creating a custom skill 14:18 - artifacts 15:11 - going from one to many agents (profiles and personas) 18:12 - agents working as a team (Hermes Kanban) 19:01 - outro I have also written an article on Hermes masterclass, the same is quoted below.

The Hermes Desktop App is insanely good. It's now the best way to run AI agents on your computer. Here's the full setup, start to finish. Enjoy! Chapters: 00:00 - why Hermes desktop is a game changer 00:46 - downloading and installing the desktop app 01:47 - picking your model and provider 02:52 - sessions, settings, and gateway connection 04:08 - adding a custom MCP server 04:58 - memory and context (the three-tier system) 06:52 - connecting to Telegram 09:45 - skills and tools 11:06 - the skills hub (built-in and community skills) 11:50 - creating a custom skill 14:18 - artifacts 15:11 - going from one to many agents (profiles and personas) 18:12 - agents working as a team (Hermes Kanban) 19:01 - outro I have also written an article on Hermes masterclass, the same is quoted below.

102,942 views • 1 month ago

Turn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies, broken paths, environment config, and hardware assumptions. From there it designs a minimal reproduction. That means a smaller model, fewer steps, and a single GPU instead of a cluster, scaled down just enough to test whether the headline claim holds. The whole run is live and fully logged. Loss curves, metrics, and training progress are all observable as it happens. What comes back is a clean signal on whether the minimal run matches the paper's reported result, plus an estimate of what a full replication would cost in compute and time. A lot of research code dies in setup before anyone verifies a single number. This moves reproduction from a weekend of debugging to a url change. Pick a paper and try it now. video credits: alphaXiv

Turn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies, broken paths, environment config, and hardware assumptions. From there it designs a minimal reproduction. That means a smaller model, fewer steps, and a single GPU instead of a cluster, scaled down just enough to test whether the headline claim holds. The whole run is live and fully logged. Loss curves, metrics, and training progress are all observable as it happens. What comes back is a clean signal on whether the minimal run matches the paper's reported result, plus an estimate of what a full replication would cost in compute and time. A lot of research code dies in setup before anyone verifies a single number. This moves reproduction from a weekend of debugging to a url change. Pick a paper and try it now. video credits: alphaXiv

45,720 views • 27 days ago

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

42,800 views • 25 days ago

Everyone is sleeping on this new OCR model! - 85.9% (sota) on olmocr bench - 90+ language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support 100% open-source.

Everyone is sleeping on this new OCR model! - 85.9% (sota) on olmocr bench - 90+ language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support 100% open-source.

167,738 views • 3 months ago

If you use LLM-as-judge, this one is for you. (bookmark it) Most teams validate their agent's outputs by calling a frontier model as the judge. It works, until it doesn't. Three problems stack up fast: → Cost: you're hitting a frontier API on every turn, every tool call, every response. In production that burns millions. → Latency: bigger models, remote calls, slow reasoning on every check. → Blind spots: frontier models don't actually know your domain. In finance, insurance, or healthcare, they miss the keywords and principles your work depends on. So I walk through a different approach: train your own small LLM judge. Instead of a giant model, you start with a small one and let the system generate the training data for you. It decomposes your domain, samples synthetic examples, runs them through a debate arena where judges reach consensus, then trains on the refined set. The result is a judge that's cheaper, faster, and more accurate on your data than Gemini, Claude, or GPT, with an OpenAI-compatible endpoint you can even deploy on-prem. I show the whole thing end to end, using a Claude Code plugin and a web interface, with a real insurance RAG grounding evaluator as the example. You can get the plugin here: Here's the full breakdown: 00:00 - Intro 00:12 - Three problems with using frontier LLMs as judges 01:05 - A different approach: train your own small judge 01:31 - How it works (synthetic data and a debate arena) 02:50 - Installing the Claude Code plugin 04:03 - Defining your task with /eval 04:34 - Example: an insurance RAG grounding evaluator 05:51 - Kicking it off and giving early feedback 06:26 - Choosing labels, domain, and strictness 08:30 - The web interface and dashboard 09:52 - Bringing your own example data (optional) 10:26 - The finished model: endpoint, accuracy, and speed 11:16 - Control, on-prem deployment, and interpretability 11:57 - Benchmarks vs frontier models and the GitHub repo 12:30 - Outro I worked with the Plurai team on this. Thanks for sponsoring the video.

If you use LLM-as-judge, this one is for you. (bookmark it) Most teams validate their agent's outputs by calling a frontier model as the judge. It works, until it doesn't. Three problems stack up fast: → Cost: you're hitting a frontier API on every turn, every tool call, every response. In production that burns millions. → Latency: bigger models, remote calls, slow reasoning on every check. → Blind spots: frontier models don't actually know your domain. In finance, insurance, or healthcare, they miss the keywords and principles your work depends on. So I walk through a different approach: train your own small LLM judge. Instead of a giant model, you start with a small one and let the system generate the training data for you. It decomposes your domain, samples synthetic examples, runs them through a debate arena where judges reach consensus, then trains on the refined set. The result is a judge that's cheaper, faster, and more accurate on your data than Gemini, Claude, or GPT, with an OpenAI-compatible endpoint you can even deploy on-prem. I show the whole thing end to end, using a Claude Code plugin and a web interface, with a real insurance RAG grounding evaluator as the example. You can get the plugin here: Here's the full breakdown: 00:00 - Intro 00:12 - Three problems with using frontier LLMs as judges 01:05 - A different approach: train your own small judge 01:31 - How it works (synthetic data and a debate arena) 02:50 - Installing the Claude Code plugin 04:03 - Defining your task with /eval 04:34 - Example: an insurance RAG grounding evaluator 05:51 - Kicking it off and giving early feedback 06:26 - Choosing labels, domain, and strictness 08:30 - The web interface and dashboard 09:52 - Bringing your own example data (optional) 10:26 - The finished model: endpoint, accuracy, and speed 11:16 - Control, on-prem deployment, and interpretability 11:57 - Benchmarks vs frontier models and the GitHub repo 12:30 - Outro I worked with the Plurai team on this. Thanks for sponsoring the video.

29,586 views • 18 days ago

Software engineers are going to love this! I found an open-source error monitoring agent that scans production logs, finds the root cause, and sends a Slack message with full context before you even notice something broke. Cuts down production downtime by 95%! Check this:

Software engineers are going to love this! I found an open-source error monitoring agent that scans production logs, finds the root cause, and sends a Slack message with full context before you even notice something broke. Cuts down production downtime by 95%! Check this:

181,290 views • 4 months ago

Claude Skills might be the biggest upgrade to AI agents so far! Some say it's even bigger than MCP. I've been testing skills for the past 3-4 days, and they're solving a problem most people don't talk about: agents just keep forgetting everything. In this video, I'll share everything I've learned so far. It covers: > The core idea (skills as SOPs for agents) > Anatomy of a skill > Skills vs. MCP vs. Projects vs. Subagents > Building your own skill > Hands-on example Skills are the early signs of continual learning, and they can change how we work with agents forever! Here's everything you need to know:

Claude Skills might be the biggest upgrade to AI agents so far! Some say it's even bigger than MCP. I've been testing skills for the past 3-4 days, and they're solving a problem most people don't talk about: agents just keep forgetting everything. In this video, I'll share everything I've learned so far. It covers: > The core idea (skills as SOPs for agents) > Anatomy of a skill > Skills vs. MCP vs. Projects vs. Subagents > Building your own skill > Hands-on example Skills are the early signs of continual learning, and they can change how we work with agents forever! Here's everything you need to know:

286,133 views • 8 months ago

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

61,971 views • 1 month ago

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

86,515 views • 2 months ago

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.

477,685 views • 1 year ago

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

51,370 views • 1 month ago

Make Claude Code 10x more powerful. Claude-Mem is a free plugin to persist memory across Claude sessions. It captures tool usage, so you always start where you left off. Endless Mode allows 95% token reduction & 20x more tool use before context exhaustion. 100% open-source.

Make Claude Code 10x more powerful. Claude-Mem is a free plugin to persist memory across Claude sessions. It captures tool usage, so you always start where you left off. Endless Mode allows 95% token reduction & 20x more tool use before context exhaustion. 100% open-source.

184,171 views • 7 months ago

A 100% open-source alternative to n8n! Sim is a drag-and-drop UI for creating powerful AI agent workflows: - Runs locally on your machine - Works with local LLMs I built a stock market research agent & connected it to Telegram in minutes. Here's a step-by-step guide:

A 100% open-source alternative to n8n! Sim is a drag-and-drop UI for creating powerful AI agent workflows: - Runs locally on your machine - Works with local LLMs I built a stock market research agent & connected it to Telegram in minutes. Here's a step-by-step guide:

176,377 views • 7 months ago

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

252,074 views • 11 months ago

i decided to put together all my AI engineering posts in a single pdf. it covers: > LLM foundations > prompt engineering > fine-tuning > RAG > context engineering > AI agents > MCP > optimization > deployment > eval and observability 375+ pages. download link in next tweet!

i decided to put together all my AI engineering posts in a single pdf. it covers: > LLM foundations > prompt engineering > fine-tuning > RAG > context engineering > AI agents > MCP > optimization > deployment > eval and observability 375+ pages. download link in next tweet!

159,856 views • 6 months ago