Zubair Sapi

You don’t need Mythos, just learn how to use Qwen 3.5 27B and Gemma 4 31B and you’ll realize you have so much intelligence under your control on a single GPU

@KaranVaidya6 @composio Good luck, hope more success in your wonderful work

Your AI agent is in bed with you. No protection. You just wanted it to work. Gmail. Allow. Calendar. Allow. Slack, Notion, GitHub. Allow. Allow. Allow. Every password, handed over. Your agent never needed a single one. They just needed @Composio Secure your agents in minutes ↓ composio.dev/protection

BigLaw firms will either reply to every email within 10 minutes or will take 3 business days to send availability for a call

A judgment answers the law. A resolution solves a business. Legal closure ≠ business closure. #ADR #Mediation #Arbitration #DisputeResolution #LegalTech

The U.S. Securities and Exchange Commission said on Tuesday the agency obtained orders for monetary relief totaling $17.9 billion during fiscal year 2025 and that it had filed 456 enforcement actions during that period. reuters.com/legal/governme…

More lawyers misusing AI (and more): "As this court already has explained at length, ... every lawyer knows that citing fake cases in a court filing is a terrible decision." Sanctions: -Lawyer and his firm to pay ~$47,000 in fees to defendants. -Lawyer and firm must send copy or order to all clients, opposing counsel, every lawyer in the firm, and every judge in every pending case. -Kicked off the case. -Court will send order to Alabama State Bar for further proceedings.

barely matters what transactional practice area you pick, or the assets you're working on. you're just mastering a set of docs. but smart and fair clients and coworkers change everything.

Join us on April 21 for our AI in Practice meeting with Dr. Gideon Christian (UCalgary). He will discuss confidentiality and privilege in the context of AI and law. Don't miss it! ✅ Free and exclusive access for CBA members 👉 bit.ly/46PYMzW

@Legaltech_news How this can help a law firm or a counsel?

Outside Counsel Selection Platform Priori Adds Agentic AI Features to RFP Offering law.com/legaltechnews/…

🚨 Notion charges you $16/month and still owns your data lol AppFlowy gives you the same workspace docs, wikis, AI, databases, kanban, project management and lets you self-host the entire thing for free. Here's what makes it different from every other Notion clone: The data ownership is real, not marketing language. You deploy it on your own server. Your files never touch their infrastructure. If they shut down tomorrow, nothing changes for you. The AI is built into the editor, not bolted on as an upsell. Summarize, rewrite, fix grammar, generate content, translate all directly inside the document without switching tools. AppFlowy Sites lets you publish any page as a live public website in one click. Internal wiki becomes external documentation instantly. The database layer supports grid, board, calendar, and gallery views all pointing at the same underlying data. Switch views without moving anything. Works natively on macOS, Windows, Linux, iOS, and Android from a single Flutter and Rust codebase. Not Electron. Actually native. github.com/AppFlowy-IO/Ap… AGPL-3.0 License. 100% Opensource. I'm switching from Notion to this... what's your plan?

Introducing... Gemma 4 Multimodal Fine-Tuner for  Apple Silicon - LoRA fine-tunning toolkit for Gemma LLM - runs locally on macOS via PyTorch and Metal - streams data from Google Cloud to your machine - fine-tune on audio, image and text - easy-to-use CLI wizard If you want to fine-tune the new Gemma 4 on text, images, or audio without renting an H100 or copying a terabyte of data to your laptop, this is the only toolkit that does it all on Apple Silicon.

Does a law degree pay off? New study says yes reut.rs/47KUWs5 reut.rs/47KUWs5

A raw LLM is just like a CPU without OS. It can compute. But it can't do anything useful on its own. This analogy is the clearest way I've found to understand what an agent harness actually does. Here's the mapping: • 𝗖𝗣𝗨 → 𝗟𝗟𝗠 (model weights). The raw compute engine. Powerful, but useless without infrastructure around it. • 𝗥𝗔𝗠 → 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝘄𝗶𝗻𝗱𝗼𝘄. Fast, always available, but limited. When it fills up, you start losing things. • 𝗛𝗮𝗿𝗱 𝗱𝗶𝘀𝗸 → 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗕 / 𝗹𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝘀𝘁𝗼𝗿𝗮𝗴𝗲. Large capacity, but slow to access. You retrieve from it, not compute in it. • 𝗗𝗲𝘃𝗶𝗰𝗲 𝗱𝗿𝗶𝘃𝗲𝗿𝘀 → 𝗧𝗼𝗼𝗹 𝗶𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗼𝗻𝘀. The interfaces that let the model interact with the outside world. Code execution, web search, file I/O. • 𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝘀𝘆𝘀𝘁𝗲𝗺 → 𝗔𝗴𝗲𝗻𝘁 𝗵𝗮𝗿𝗻𝗲𝘀𝘀. This is the key layer. It manages everything: which tools to call, what fits in memory, when to retrieve, how to recover from errors, and when to stop. And then there's the 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 layer. That's the "agent" itself. Not a piece of software you install, but emergent behavior that arises when the OS does its job well. This is why two products using the exact same model can perform completely differently. LangChain changed only their harness infrastructure (same model, same weights) and jumped from outside the top 30 to rank 5 on TerminalBench 2.0. The model didn't improve. The operating system around it did. The article below is a deep dive on agent harness engineering, covering the orchestration loop, tools, memory, context management, and everything else that transforms a stateless LLM into a capable agent.

A MIT student figured out how to compress an entire semester of lecture content into one 90-minute study session. He calls it "context stacking," and it's the most unfair thing I've seen done with NotebookLM. I asked him to walk me through it. He did. I haven't studied the same way since. Here's exactly what he does. Two days before each lecture, he uploads everything into NotebookLM. The assigned readings, the previous week's slides, 3 or 4 related papers he finds himself, and any problem sets that are still open. Most students wait for the lecture to explain the material. He walks in having already built a mental model of it. That's step one. But it's not the move that makes it unfair. The first prompt he runs across all of it: "What are the 5 core concepts this week's content is built on, and how do they connect to what I studied last week?" Not summarize. Not define. Connect. NotebookLM pulls threads across everything he uploaded simultaneously. It surfaces relationships between ideas that would take a normal student weeks of review to notice. He gets that map before the lecture even starts. Then he runs the prompt that does most of the work. "What would I need to genuinely understand about this material to be able to teach it to someone with zero background in this subject?" That question is doing something most students never force themselves to do. It exposes exactly where his understanding is solid and exactly where it's hollow. The gaps show up immediately, and he spends the rest of the 90 minutes filling only those gaps. Not reviewing what he already knows. Only fixing what he doesn't. The final prompt is the one that separates context stacking from every other study method I've heard of. "What question could a professor ask about this material that would expose a student who understood the surface but missed the underlying logic?" He's not studying for the exam he expects. He's studying for the exam designed to catch people who only think they understood it. By the time he sits in the lecture hall, the professor is not teaching him anything new. The professor is confirming what he already mapped, filling in a few details, and occasionally surprising him with something he didn't anticipate. That surprise is the only thing he writes down. Most students leave a lecture hoping the material will eventually click. He walks in with it already clicked, and uses the lecture to find out what he missed. That's not a study hack. That's a completely different relationship with learning.

Harvey: ~$1B raised across 4 rounds in 14 months. Legora: ~$800M across 3 rounds in 10 months. Combined $1.7B+ into two legal AI companies. History doesn't repeat, it rhymes. This is the Capital Wars playbook we've seen before 🧵

💡 A clearer way to predict ICC Arbitration costs with the ICC Costs Calculator. 🔍 How it works: 1️⃣ Enter the amount in dispute 2️⃣ Select your procedure: ordinary or expedited 3️⃣ Indicate the number of arbitrators 👉 Try it now: bit.ly/4scP8ih

🚨 BREAKING: Microsoft launches a free Python library that converts ANY document to Markdown Introducing Markitdown. Let me explain. 🧵

Gemma 4 models are now on Mac! Try the new Gemma 4 E2B and E4B — Google’s most intelligent open models for the edge, powered by MLX for best-in-class performance on M-series chips. Update your Mac app now.

Lawyer to Lawyer: It’s not about the number of case files in your office, it’s about the quality of your service and the fortune you derive from it.