Muratcan Koylan
@koylanai • 20,208 subscribers
Member of Technical Staff, Research @sullyai | prev: AI Agent Systems Manager, 99Ravens
Videos
Since I posted my Personal OS / filesystem article, LLM personal knowledge bases have turned into a real topic in the AI world. I’ve been building this system in Cursor for almost two years, but I wasn’t expecting to end up talking with people like a YouTube co-founder, a NASCAR driver, or some of the AI leaders I respect most because of that post. For me it was the first signal that this wasn’t niche anymore. The biggest pushback on the article was whether a filesystem is enough or scalable for something like this. Scaling the vault is easy; scaling curation and placement is not. Karpathy’s LLM Wiki published soon after with same thesis and it was an independent validation for me. "LLM incrementally builds and maintains a persistent wiki structured, interlinked markdown between you and the raw sources." Now there are tons of similar projects, different takes on the same idea. That’s good, I’m also evolving my own stack from what’s out in the open, and honestly, reframing the personal filesystem as a wiki is a smart move. I’m posting this because I think the harder problem is still the knowledge transfer pipeline. Designing a Personal OS (aka personal knowledge base) is the easy part. The architecture only starts to pay off when you fill it for years -not just posts you liked, but decision patterns, career and life details, half-formed thoughts, writing, the messy stuff. Getting all of that into the right markdown file, at the right time, in the right shape is still the bottleneck. I built a Chrome extension (Feed2Context, details in the article) that grabs a post with my notes from my feed, drops it into the filesystem, and my agents synthesize and route it. I also built OpenHome assistant as a voice pipeline from my room into the wiki. Plus a bunch of MCP hooks into my accounts. But orchestrating all these helpers gets exhausting. A lot of people suggested Obsidian but I'm mostly on Readwise CLI to pull from X, LinkedIn, arXiv, books, and news. It works well on mobile, and because it’s a CLI, agents can find what they need and push it into the filesystem. Skill registries help a lot, in the videos I’ve got flows like Readwise CLI + alphaXiv MCP for research papers: save a paper, agent pulls the full text, analyzes it, teaches me back. I’m also testing Zapier CLI, and waiting for especially the Triggers API, between things like Yutori or plain cron, keeping a personal wiki alive is still hard; nobody wants to be the cron job for their own life, so triggers might be part of the answer. TL;DR: A personal filesystem you control isn’t optional if you don’t want to rent your memory from one AI company. The open problem is keeping it fed and current. What I actually want is one solution that can watch my screen, hear my voice, read my accounts, and write into my Personal OS without me acting as the integration layer forever.
Muratcan Koylan75,479 Aufrufe • vor 1 Monat
Most "agentic" failures happen because the model lacks specific domain knowledge. Here I'm showing how loading a Skills Plugin solves that for dataset generation. I turned a research paper (shows fine-tuning dataset creation from books) into a Skill and just gave a book link and asked it to generate the dataset. Claude Code produced a clean SFT-ready dataset from a single URL. The same process can be applied to anything.
Muratcan Koylan102,561 Aufrufe • vor 5 Monaten
🔻My First GPT-4 Project 🔻 I can chat with thousands of pages fast and affordably. How? Let's try with the latest World Economic Forum report (2023 April) Built with OpenAI, Pinecone and 1. Upload the PDF and divide its text into chunks. 2. Store the embeddings in your VectorStore. 3. Connect your Chat GPT-4 and restrict it to providing answers solely from the given document. It's truly a game-changer for a no-coder.
Muratcan Koylan492,124 Aufrufe • vor 3 Jahren
OpenAI wants markdown structure. Anthropic prefers XML tags. Google emphasizes few-shot examples. So I built a simple agent system that reads the official prompting docs and applies them to the given prompt. Each optimizer runs a ReAct loop: - list_provider_docs → discover available guidelines - read_provider_doc → fetch specific content - submit_optimization → return structured result Agent decides what context it needs. The loop runs until submission: 1. LLM reasons about the task 2. Calls a tool 3. Observes result 4. Repeats Typically 3-4 iterations. Parallel execution via asyncio.gather; all providers optimize concurrently. Good to explore the agent design and prompts. Feel free to play with it. Shared the repo here: @LangChainAI OpenRouter
Muratcan Koylan62,021 Aufrufe • vor 6 Monaten
I've built it for you!! It's an automated AI system that analyzes AI case studies (you can change the use case) to identify and document enterprise-level AI implementations. It starts by reading URLs from a CSV file and uses web scraping (either through WebLoader or Firecrawl) to extract the content from each case study. The extracted content is then sent to Claude 3.5 Sonnet, which analyzes whether the case study represents a genuine enterprise AI implementation based on specific criteria like company maturity, implementation scale, and measurable business outcomes. For each URL, the system first saves the raw content and then performs this initial qualification analysis. If Claude determines that a case study qualifies as an enterprise AI implementation, the system proceeds to generate a detailed analysis. It creates three types of reports: - an individual case study report with sections like Executive Summary, AI Strategy Analysis, and Business Impact Assessment - a cross-case analysis that identifies patterns and trends across multiple case studies - and an executive dashboard summarizing key metrics and insights. All of these reports are saved in structured formats (markdown for individual reports, JSON for cross-case analysis and dashboard) in their respective directories. If a case study doesn't qualify as an enterprise AI implementation, the system logs the reason and moves on to the next URL. The entire process is asynchronous and provides detailed terminal feedback about its progress and decisions.
Muratcan Koylan85,198 Aufrufe • vor 1 Jahr
I replaced a $2000/month predictive analysis software with Julius AI. In this video, I'll show you how to create a complex B2B marketing dataset using GPT. Then, I'll identify companies with a high likelihood of churn, determining their reasons for doing so. Julius AI achieves this using a chain of deterministic actions to leverage various machine learning models. This tool is incredibly powerful, and I'm excited to share my process with you.
Muratcan Koylan53,670 Aufrufe • vor 1 Jahr
Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.
Muratcan Koylan27,005 Aufrufe • vor 2 Jahren
Keine weiteren Inhalte verfügbar