Gul Saeed Khattak

Jansen Huang NVIDIA CEO has resigned. Links in replies 🔽🔽🔽👇

𝗔𝗪𝗦 𝗝𝘂𝘀𝘁 𝗣𝘂𝘁 𝗮 𝗖𝗼𝗽𝘆 𝗼𝗳 𝗜𝘁𝘀 𝗖𝗹𝗼𝘂𝗱 𝗼𝗻 𝗬𝗼𝘂𝗿 𝗟𝗮𝗽𝘁𝗼𝗽: AWS released AWS Emulator on 11 November and has already crossed 3.6K likes. From the README, it's a local emulator of the AWS APIs that you can test against "𝘸𝘪𝘵𝘩𝘰𝘶𝘵 𝘤𝘢𝘭𝘭𝘪𝘯𝘨 𝘈𝘞𝘚", on a laptop, a dev server or in CI The unusual part is who built it. AWS says 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝘄𝗿𝗼𝘁𝗲 𝘁𝗵𝗲 𝗰𝗼𝗱𝗲, and no human reviewed it. It isn't a demo, either. It's a public release with 𝟮𝟵,𝟲𝟴𝟰 𝗰𝗼𝗺𝗺𝗶𝘁𝘀, and 𝗮𝗯𝗼𝘂𝘁 𝟯,𝟲𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀 as of 12 November. Local AWS cloud emulation has been a crowded corner for years. Azure and Google Cloud have their own options, but they come mostly one service at a time (Azurite for Azure Storage, the gcloud emulators for Pub/Sub and Firestore). AWS Focused Map: • 𝗟𝗼𝗰𝗮𝗹𝗦𝘁𝗮𝗰𝗸: the default for a long time. Its packaging changed in March 2026, and the free Hobby tier is for non-commercial use only. • 𝗠𝗼𝘁𝗼: Python mocks, great inside unit tests. • 𝗙𝗹𝗼𝗰𝗶, 𝗠𝗶𝗻𝗶𝗦𝘁𝗮𝗰𝗸: free MIT projects pitched as LocalStack replacements. 𝗦𝗼 𝘄𝗵𝗲𝗿𝗲 𝗱𝗼𝗲𝘀 𝗔𝗪𝗦'𝘀 𝗼𝘄𝗻 𝗳𝗶𝘁? AWS Emulator is the first one made by the cloud provider itself. Free, public domain, and reportedly covering 𝟮𝟬𝟬+ 𝘀𝗲𝗿𝘃𝗶𝗰𝗲𝘀. he community spent this year filling the hole LocalStack left. Now AWS has walked into that hole itself, and 𝗻𝗲𝗶𝘁𝗵𝗲𝗿 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 𝗻𝗼𝗿 𝗚𝗼𝗼𝗴𝗹𝗲 𝗵𝗮𝘀 𝗱𝗼𝗻𝗲 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝘆𝗲𝘁. Probably they will follow the suit. Things to be careful about: • 𝗧𝗲𝗹𝗲𝗺𝗲𝘁𝗿𝘆 𝗶𝘀 𝗼𝗻 𝗯𝘆 𝗱𝗲𝗳𝗮𝘂𝗹𝘁. Turn it off with --𝚝𝚎𝚕𝚎𝚖𝚎𝚝𝚛𝚢 𝚘𝚏𝚏 or 𝙴𝙼𝚄𝙻𝙰𝚃𝙾𝚁_𝚃𝙴𝙻𝙴𝙼𝙴𝚃𝚁𝚈=𝚘𝚏𝚏. • 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝘀𝗼𝘂𝗿𝗰𝗲 𝗻𝗲𝗲𝗱𝘀 𝗮𝗯𝗼𝘂𝘁 𝟭𝟬𝟬 𝗚𝗕 of disk and works on Linux only. • It's meant for building and testing, 𝗻𝗼𝘁 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝗼𝗿 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝘁𝗲𝘀𝘁𝗶𝗻𝗴. • The "200+ services" figure comes from coverage, not from my own count. Check the per-release fidelity scores for the services you actually use. Five of the most recent releases say "𝘚𝘤𝘰𝘳𝘦𝘴 𝘢𝘳𝘦 𝘯𝘰𝘵 𝘢𝘷𝘢𝘪𝘭𝘢𝘣𝘭𝘦 𝘧𝘰𝘳 𝘵𝘩𝘪𝘴 𝘳𝘦𝘭𝘦𝘢𝘴𝘦." One thing more : The project lists 𝗺𝗼𝗿𝗲 𝘁𝗵𝗮𝗻 𝟲,𝟬𝟬𝟬 𝘁𝗵𝗶𝗻𝗴𝘀 𝘁𝗵𝗮𝘁 𝗱𝗼𝗻'𝘁 𝘄𝗼𝗿𝗸 𝘆𝗲𝘁. And "no human read it" will make plenty of engineers nervous, especially in a tool that is meant to teach them how AWS behaves. What we actually know is narrow. Agents can produce very wide, testable software that a big company is willing to put its name on. We don't yet know how it holds up after months of real use. 𝘐𝘧 𝘵𝘦𝘴𝘵𝘴 𝘤𝘢𝘯 𝘴𝘵𝘢𝘯𝘥 𝘪𝘯 𝘧𝘰𝘳 𝘩𝘶𝘮𝘢𝘯 𝘳𝘦𝘷𝘪𝘦𝘸 𝘩𝘦𝘳𝘦, 𝘸𝘩𝘦𝘳𝘦 𝘦𝘭𝘴𝘦 𝘸𝘪𝘭𝘭 𝘤𝘰𝘮𝘱𝘢𝘯𝘪𝘦𝘴 𝘥𝘦𝘤𝘪𝘥𝘦 𝘵𝘩𝘢𝘵 𝘵𝘩𝘦𝘺 𝘤𝘢𝘯? Links in Replies 👇👇👇

CRAZY !!:🔇👄 Claude Can Lip Read : I Muted MoonShots Podcast and Asked Claude to Read Their Lips I screen-recorded a short clip from @moonshots_pod with @PeterDiamandis and @DaveBlundin Here's what I did. I screen-recorded a short clip from Moonshots with Peter Diamandis, about 50 seconds where the guest talks about AI chips ending up in China and the investigation around it. I stripped the audio out in CapCut. The file still had a sound track, but it was pure silence. Then I gave it to Claude (Opus 5.5) and said: lip read this. I recorded my whole screen while it worked. That's the video attached. What it did on its own: • Found a real lip-reading model: Auto-AVSR, open-source research from Imperial College London. Code from GitHub, the 1 GB model file from Hugging Face. • Checked the download: it compared the file's fingerprint with the one in the official README before trusting it. • Did the video work: found the scene cuts, cropped the area around the face, and split it into 6 short clips at the frame rate the model expects. • Ran it on a plain cloud CPU. No GPU. Note: I asked Claude: did you run this on my computer? Its answer: no. It ran in its own cloud sandbox, a machine with 4 CPU cores and 15 GB of memory. No GPU. It didn't go smoothly the whole way, which I liked. Hugging Face's download server was blocked, so it asked me to allow it. Then a safety check refused to run code downloaded from the internet, and it stopped and asked me instead of finding a way around it. Then the transcript came back. Lines like "a very big deal", "a huge number of chips", "Chinese models", "illegal imports" and "technically probably not illegal, maybe it is, maybe it isn't… that's the part where they're just gonna dig in." From a silent video. That part still gets me. It isn't perfect, and it told me so. Some lines were pure nonsense, like "the dry era of soybean play and the waistband." "Trading Chinese models" was almost certainly "training". Lip reading is hard because lots of words look the same on the lips. This model gets about 1 word in 5 wrong even on clean test videos, and mine was a phone recording of a video call. So it's not a transcript. But I knew what the conversation was about, and some sentences read like real speech. A few years ago this was a research demo. Now it's one prompt and a bit of patience. What else is hiding in all the muted videos we scroll past?

Agent_Skills: A Trading Firm Open-Sourced a Tutor, Not a Trading Bot One of Wall Street’s most secretive trading firms just open-sourced something. It isn’t a trading bot. It’s a tutor that refuses to give you the answer. 𝗝𝗮𝗻𝗲 𝗦𝘁𝗿𝗲𝗲𝘁'𝘀 𝗙𝗶𝗿𝘀𝘁 𝗣𝘂𝗯𝗹𝗶𝗰 𝗔𝗜 𝗦𝗸𝗶𝗹𝗹 𝗪𝗼𝗻'𝘁 𝗚𝗶𝘃𝗲 𝗬𝗼𝘂 𝘁𝗵𝗲 𝗔𝗻𝘀𝘄𝗲𝗿 You ask an AI to explain something. It writes a lovely answer, you nod along, and a week later you couldn't explain it to anyone. 𝗝𝗮𝗻𝗲 𝗦𝘁𝗿𝗲𝗲𝘁'𝘀 𝗳𝗶𝘅 𝗶𝘀 𝗮 𝘁𝘂𝘁𝗼𝗿 𝘁𝗵𝗮𝘁 𝗿𝗲𝗳𝘂𝘀𝗲𝘀 𝘁𝗼 𝗹𝗲𝗰𝘁𝘂𝗿𝗲. On 3 November the quant firm opened a GitHub repo called agent_skills. It holds exactly one skill, socratic-tutor. It's a single SKILL.md file of about 𝟴𝟰𝟱 𝘄𝗼𝗿𝗱𝘀. No code, no app, MIT licence. Nine days later it has 𝟱,𝟴𝟭𝟴 𝘀𝘁𝗮𝗿𝘀 𝗮𝗻𝗱 𝟰𝟬𝟮 𝗳𝗼𝗿𝗸𝘀 (as of 12 Nov). Part of that is the name. Jane Street usually keeps quiet, so a public AI release got attention fast, and the twist that it's a teacher and not a trading bot did the rest on X. 𝗛𝗲𝗿𝗲'𝘀 𝘄𝗵𝗮𝘁 𝘁𝗵𝗲 𝗳𝗶𝗹𝗲 𝘁𝗲𝗹𝗹𝘀 𝘁𝗵𝗲 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗱𝗼. • 𝗣𝗹𝗮𝗰𝗲𝗺𝗲𝗻𝘁 𝗳𝗶𝗿𝘀𝘁: split your topic into 4 to 10 subskills, then ask 3 to 5 questions before teaching anything. • 𝗔 𝘀𝗸𝗶𝗹𝗹 𝗺𝗮𝗽: every subskill sits on a 0 to 5 scale, drawn as text progress bars after each change. • 𝗢𝗻𝗲 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻 𝗮𝘁 𝗮 𝘁𝗶𝗺𝗲: the message ends at the question. No hints tacked on. • 𝗪𝗿𝗼𝗻𝗴 𝗮𝗻𝘀𝘄𝗲𝗿𝘀 𝗴𝗲𝘁 𝗮 𝗻𝗮𝗿𝗿𝗼𝘄𝗲𝗿 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻, not the answer. A direct explanation only comes after 2 or 3 failed tries, and then it re-tests you from another angle. • 𝗥𝗶𝗴𝗵𝘁 𝗮𝗻𝘀𝘄𝗲𝗿𝘀 𝗴𝗲𝘁 𝗽𝘂𝘀𝗵𝗯𝗮𝗰𝗸 sometimes, so you learn to defend them. It finishes only when every subskill reaches 4 out of 5, followed by a mixed final exam. 𝗧𝗵𝗲 𝘀𝗺𝗮𝗹𝗹 𝗿𝘂𝗹𝗲𝘀 𝗮𝗿𝗲 𝘁𝗵𝗲 𝗶𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗽𝗮𝗿𝘁. • 𝗔 𝗹𝗲𝘃𝗲𝗹 𝗼𝗻𝗹𝘆 𝗴𝗼𝗲𝘀 𝘂𝗽 𝗮𝗳𝘁𝗲𝗿 𝟮 𝘀𝗲𝗽𝗮𝗿𝗮𝘁𝗲 𝗰𝗵𝗲𝗰𝗸𝘀, and one has to be "𝘶𝘯𝘱𝘳𝘰𝘮𝘱𝘵𝘦𝘥 𝘳𝘦𝘤𝘢𝘭𝘭", not repeating what you were just told. • It is told: "𝘋𝘰 𝘯𝘰𝘵 𝘢𝘵𝘵𝘳𝘪𝘣𝘶𝘵𝘦 𝘵𝘰 𝘵𝘩𝘦 𝘶𝘴𝘦𝘳 𝘢𝘯𝘺 𝘪𝘯𝘴𝘪𝘨𝘩𝘵 𝘵𝘩𝘦𝘺 𝘥𝘪𝘥 𝘯𝘰𝘵 𝘢𝘤𝘵𝘶𝘢𝘭𝘭𝘺 𝘦𝘹𝘱𝘳𝘦𝘴𝘴." That's a direct guard against the model flattering you. • 𝗟𝗲𝘃𝗲𝗹 𝟱 𝗺𝗲𝗮𝗻𝘀 𝘆𝗼𝘂 𝗰𝗮𝗻 𝘁𝗲𝗮𝗰𝗵 𝗶𝘁. You have to handle an edge case and explain it well enough that the model would trust you to teach it. • If it can run tools, it checks 𝘆𝗼𝘂𝗿 𝗮𝗰𝘁𝘂𝗮𝗹 𝗼𝘂𝘁𝗽𝘂𝘁 rather than your description of it. 𝗙𝗼𝗿 𝗹𝗲𝗮𝗿𝗻𝗲𝗿𝘀: paste the file into ChatGPT, Claude or Gemini, or drop the folder into a coding agent's skills folder, and say "teach me X". Good for things you think you understand until someone asks. Is it new? Not as an idea. ChatGPT Study Mode, Gemini Guided Learning and Claude's learning mode all teach by asking questions. What's different here is a plain, strict rulebook you can read in five minutes and run on any model. One caveat: there's no evaluation in the repo showing it teaches better. 𝘛𝘩𝘦 𝘣𝘦𝘴𝘵 𝘈𝘐 𝘵𝘶𝘵𝘰𝘳 𝘮𝘪𝘨𝘩𝘵 𝘣𝘦 𝘵𝘩𝘦 𝘰𝘯𝘦 𝘵𝘩𝘢𝘵 𝘮𝘢𝘬𝘦𝘴 𝘺𝘰𝘶 𝘥𝘰 𝘵𝘩𝘦 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨. Links in reply 👇 Video credit: AI adventurer on YouTube (@aiadventurer-p1l). Original: youtube.com/@aiadventurer-p1…

𝗧𝗵𝗲 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗦𝗮𝗻𝗱𝗯𝗼𝘅 𝗠𝗮𝗽: 𝗖𝗹𝗼𝘂𝗱 𝘃𝘀 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲, 𝗟𝗮𝗽𝘁𝗼𝗽 𝘃𝘀 𝗦𝗲𝗿𝘃𝗲𝗿 . And where Ravit fits Agents don't always follow the rules. Give one a goal and it may take a road you never wanted, through your files, your tokens or your live data. The best-known case: in July 2025 the founder of SaaStr said Replit's agent 𝗱𝗲𝗹𝗲𝘁𝗲𝗱 𝗵𝗶𝘀 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 during a code freeze. Replit's CEO apologised. That's why sandboxes got popular. A sandbox is a sealed-off computer for the agent, so a mistake stays inside it. Here's how I'd draw the map. 𝗟𝗲𝘃𝗲𝗹 𝟭: 𝗿𝗲𝗻𝘁 𝗶𝘁 𝗼𝗿 𝗿𝘂𝗻 𝗶𝘁 • 𝗖𝗹𝗼𝘂𝗱: AWS, Azure, Cloudflare, E2B, Daytona, Modal, Vercel and many more. One public benchmark tracks 𝟯𝟬 𝗽𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀, and prices vary widely • 𝗢𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲: you run it yourself, on a laptop or on your own servers. A cheap server is enough to start (Hetzner's begin at about €5.49 a month) The rest of this post is about open source. 𝗟𝗲𝘃𝗲𝗹 𝟮: 𝘁𝘄𝗼 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀 𝗦𝗮𝗳𝗲𝘁𝘆 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲: sandbox-mcp and devvm. Both ask "𝘸𝘩𝘢𝘵 𝘤𝘢𝘯 𝘵𝘩𝘦 𝘢𝘨𝘦𝘯𝘵 𝘳𝘦𝘢𝘤𝘩 𝘪𝘧 𝘪𝘵 𝘮𝘪𝘴𝘣𝘦𝘩𝘢𝘷𝘦𝘴?" • 𝘀𝗮𝗻𝗱𝗯𝗼𝘅-𝗺𝗰𝗽 gives it a clean Windows PC and throws it away afterwards • 𝗱𝗲𝘃𝘃𝗺 gives it a Linux VM that sees only one folder, with placeholders in place of your real tokens 𝗖𝗼𝘀𝘁 𝗮𝘁 𝘀𝗰𝗮𝗹𝗲 𝗼𝗻 𝘀𝗲𝗿𝘃𝗲𝗿𝘀: Sandstorm and Rivet. Both ask "𝘩𝘰𝘸 𝘥𝘰 𝘐 𝘳𝘶𝘯 𝘮𝘢𝘯𝘺 𝘢𝘨𝘦𝘯𝘵𝘴 𝘤𝘩𝘦𝘢𝘱𝘭𝘺 𝘸𝘩𝘦𝘯 𝘵𝘩𝘦𝘺 𝘮𝘰𝘴𝘵𝘭𝘺 𝘸𝘢𝘪𝘵?" • 𝗦𝗮𝗻𝗱𝘀𝘁𝗼𝗿𝗺 keeps the sandbox and puts it to sleep • 𝗥𝗶𝘃𝗲𝘁 takes the agent's memory and loop out of the sandbox, so there is far less to keep alive Why split it like this? The first two are for one developer while building. The other two are for running agents for many users. 𝗔 𝗰𝗹𝗼𝘀𝗲𝗿 𝗹𝗼𝗼𝗸 𝗮𝘁 𝗥𝗶𝘃𝗲𝘁 Rivet isn't a sandbox at all. It gives each agent a small Actor with its own SQLite database and a live connection, and many Actors share one Node.js process. The README claims 𝟳𝟮 𝗞𝗕 each and a 𝟰.𝟵𝟵 𝗺𝘀 cold start at p99. Its view, in its own words: "𝘈𝘯 𝘢𝘨𝘦𝘯𝘵 𝘯𝘦𝘦𝘥𝘴 𝘢 𝘴𝘢𝘯𝘥𝘣𝘰𝘹 𝘰𝘯𝘭𝘺 𝘵𝘰 𝘳𝘶𝘯 𝘤𝘰𝘥𝘦 𝘪𝘵 𝘸𝘳𝘪𝘵𝘦𝘴." Agents that only call tools need none. Agents that write code get Rivet's lighter agentOS, or call a full sandbox as a tool. 𝗛𝗼𝘄 𝘁𝗵𝗲𝘆 𝗳𝗶𝘁 𝘁𝗼𝗴𝗲𝘁𝗵𝗲𝗿 They stack more than they compete. • 𝗪𝗵𝗶𝗹𝗲 𝘆𝗼𝘂 𝗯𝘂𝗶𝗹𝗱: devvm keeps your coding agent off your real machine • 𝗪𝗵𝗶𝗹𝗲 𝘆𝗼𝘂 𝘁𝗲𝘀𝘁 𝗮 𝗪𝗶𝗻𝗱𝗼𝘄𝘀 𝗮𝗽𝗽: sandbox-mcp checks it on a clean PC • 𝗪𝗵𝗲𝗻 𝘆𝗼𝘂 𝘀𝗵𝗶𝗽 𝗮𝗻 𝗮𝗴𝗲𝗻𝘁 𝘁𝗼 𝗺𝗮𝗻𝘆 𝘂𝘀𝗲𝗿𝘀: Rivet holds each user's agent, its history and its live connection • 𝗪𝗵𝗲𝗻 𝘁𝗵𝗮𝘁 𝗮𝗴𝗲𝗻𝘁 𝗺𝘂𝘀𝘁 𝗿𝘂𝗻 𝗰𝗼𝗱𝗲: it calls a sandbox, and Sandstorm keeps those sandboxes cheap while idle 𝗪𝗵𝗶𝗰𝗵 𝗼𝗻𝗲 𝘀𝘂𝗶𝘁𝘀 𝘆𝗼𝘂 • 𝗨𝘀𝗲𝗿𝘀: running a coding agent on your own laptop? Start with devvm (Mac, Linux) or sandbox-mcp (Windows Pro) • 𝗕𝘂𝗶𝗹𝗱𝗲𝗿𝘀: shipping an agent to many people? Look at Rivet for its memory, and add a sandbox only if it runs code • 𝗢𝗿𝗴𝗮𝗻𝗶𝘀𝗮𝘁𝗶𝗼𝗻𝘀: want it all on your own servers? All four are open source, and Sandstorm is the one built to pack many sandboxes onto small machines 𝗧𝗵𝗲 𝗵𝗼𝗻𝗲𝘀𝘁 𝗹𝗶𝗺𝗶𝘁𝘀, 𝗼𝗻𝗲 𝗲𝗮𝗰𝗵 • 𝘀𝗮𝗻𝗱𝗯𝗼𝘅-𝗺𝗰𝗽: one sandbox at a time, and no Windows Home • 𝗱𝗲𝘃𝘃𝗺: no Windows, and code in the VM can still use your GitHub token through the proxy • 𝗦𝗮𝗻𝗱𝘀𝘁𝗼𝗿𝗺: if 10 or more sandboxes wake at once on a small server, 𝗼𝗻𝗹𝘆 𝗮𝗯𝗼𝘂𝘁 𝟲 𝗴𝗲𝘁 𝗮𝗻𝘀𝘄𝗲𝗿𝗲𝗱 • 𝗥𝗶𝘃𝗲𝘁: TypeScript and Rust first, and no multi-region when self-hosting yet For all four, 𝘁𝗵𝗲 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗻𝘂𝗺𝗯𝗲𝗿𝘀 𝗰𝗼𝗺𝗲 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝗺𝗮𝗸𝗲𝗿𝘀 𝘁𝗵𝗲𝗺𝘀𝗲𝗹𝘃𝗲𝘀. 𝘗𝘪𝘤𝘬 𝘣𝘺 𝘵𝘩𝘦 𝘲𝘶𝘦𝘴𝘵𝘪𝘰𝘯 𝘺𝘰𝘶'𝘳𝘦 𝘢𝘴𝘬𝘪𝘯𝘨. 𝘐𝘴 𝘪𝘵 "𝘸𝘩𝘢𝘵 𝘤𝘢𝘯 𝘪𝘵 𝘳𝘦𝘢𝘤𝘩?" 𝘰𝘳 "𝘸𝘩𝘢𝘵 𝘥𝘰𝘦𝘴 𝘪𝘵 𝘤𝘰𝘴𝘵 𝘸𝘩𝘪𝘭𝘦 𝘪𝘵 𝘸𝘢𝘪𝘵𝘴?" Links in reply 👇

Neo4j open sourced light embedded graph database this week. No Server needed. My first reaction: oh, another Kuzu. Kuzu did this from 2022 until Apple bought it and archived the repo. LadybugDB and FalkorDB already run without a server too. So "no server" is not the news. What is different is who it is built for. Relate assumes the main user is an AI agent, not a person. That changes a lot of small decisions, and they are worth a look. The closest thing to it LadybugDB. It is the community fork of Kuzu, it runs inside your program, it speaks Cypher, and Cognee already uses it as its default graph store. If you want to know what Relate competes with, it is that. Think of a spreadsheet file versus a company database. The database is more powerful, but the spreadsheet is the thing you actually open, work in, and email to a colleague. Relate turns a graph into that kind of file. Open it, add connections, query it, close it. • It is written in Rust and comes as a CLI (a terminal tool), a Python package you can pip install it, Node and in-browser builds (WASM), plus Java, Go, Swift and C bindings. • A graph is a file. One .rl file, a folder, or pure memory that disappears when the program ends. Every change is written to a log first (a running diary of changes, so a crash does not lose your work), with Parquet snapshots saved alongside. You can commit the file to git or email it. "Can it turn my document into a graph?" No, and this is the part most people will get wrong. Relate stores and queries a graph. It does not read text and work out the people, companies and links inside it. There is no LLM inside it. So if you have a document and want a graph from it, something else has to do the reading: • An AI agent (the intended way). Claude Code or Cursor reads the document, decides what the things and connections are, and writes them into Relate with Cypher. Later, the same agent or another one queries it. The agent builds the graph. Relate holds it. • Your own script. If the data is already structured, like a CSV or JSON, you can load it straight in with Cypher, LOAD CSV, or a file of statements. No LLM needed. • Two built-in extensions that need no LLM: one turns a folder of files into a graph, one turns git history into a graph. • Vector search works, but you bring the embeddings. Relate does not create them. That is what "built for agents" means here. The agent is the builder. Relate is the notebook it writes in. Built for a model, not a person It is not the first of its kind Kuzu did embedded Cypher. LadybugDB carries that code on under MIT. FalkorDB has an embedded mode under SSPL. CozoDB does it with Datalog instead of Cypher. Relate's difference is Neo4j's query dialect and drivers, the round trip to Aura, and the agent tooling built in from day one. How to play with it • Browser playground: see the link in replies • The exe from the releases page. The simplest option. One file, run it from a terminal. • The Python wheel from the same page. It is not on PyPI yet, so download the .whl file first, pip install it, then use it in Python with "import relate". • The curl install script. Mac and Linux only, it does not cover Windows. • Docker, if you want it as a server speaking Bolt and HTTP. That is the opposite of the embedded idea, and overkill for a trial. Links in replies 👇👇

𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰'𝘀 𝗜𝗣𝗢 𝗜𝘀 𝗡𝗼𝘁 𝗣𝗿𝗶𝗰𝗲𝗱 𝗬𝗲𝘁, 𝗔𝗻𝗱 𝗧𝗵𝗲 𝗡𝘂𝗺𝗯𝗲𝗿 𝗜𝘀 𝗔𝗹𝗿𝗲𝗮𝗱𝘆 𝗠𝗼𝘃𝗶𝗻𝗴 On Tuesday, Anthropic told the market what it wants for its shares. Less than a day later, its bankers were reported to be preparing to ask for more. 𝗪𝗵𝗮𝘁 𝗧𝗵𝗲 𝗙𝗶𝗹𝗶𝗻𝗴 𝗦𝗮𝘆𝘀 • 𝗧𝗵𝗲 𝗽𝗿𝗶𝗰𝗲: $70 to $78 a share, for 825 million shares. • 𝗧𝗵𝗲 𝗿𝗮𝗶𝘀𝗲: up to $𝟲𝟰.𝟯𝟱𝗯𝗻, plus an option for the banks to sell about $9.65bn more. • 𝗧𝗵𝗲 𝘀𝗶𝗱𝗲 𝗱𝗲𝗮𝗹: another $𝟮𝟲𝗯𝗻 at the same price from seven partners: AMD, Broadcom, Google, Micron, Microsoft, Nvidia and TSMC. • 𝗧𝗵𝗲 𝘁𝗶𝗰𝗸𝗲𝗿: ANT, on Nasdaq. At the top of that range the company is valued at about $𝟭.𝟰𝘁𝗻, counting staff stock options. 𝗪𝗵𝗮𝘁 𝗖𝗵𝗮𝗻𝗴𝗲𝗱 𝗢𝘃𝗲𝗿𝗻𝗶𝗴𝗵𝘁 The Financial Times reports, citing five unnamed people, that demand was heavy and bankers now expect to price above the range. That would mean $𝟭.𝟱𝘁𝗻 𝗼𝗿 𝗺𝗼𝗿𝗲, and more than $100bn raised in total. 𝗪𝗵𝘆 𝗥𝗮𝗶𝘀𝗲 𝗦𝗼 𝗠𝘂𝗰𝗵 The filing answers it. Anthropic has signed spending commitments of about $𝟵𝟬𝟬.𝟵𝗯𝗻, almost all for computing power. About half is due before the end of 2030. Against that: revenue of $𝟭𝟳.𝟬𝗯𝗻 in the third quarter, and a run-rate of about $𝟴𝟭𝗯𝗻 at the end of October. 𝗪𝗵𝗮𝘁 𝗜𝘀 𝗡𝗼𝘁 𝗦𝗲𝘁𝘁𝗹𝗲𝗱 • 𝗡𝗼𝘁𝗵𝗶𝗻𝗴 𝗶𝘀 𝗳𝗶𝗻𝗮𝗹. Pricing is expected on 18 November. • 𝗧𝗵𝗲 $𝟭.𝟱𝘁𝗻 𝗳𝗶𝗴𝘂𝗿𝗲 is 𝘳𝘦𝘱𝘰𝘳𝘵𝘪𝘯𝘨 𝘧𝘳𝘰𝘮 𝘶𝘯𝘯𝘢𝘮𝘦𝘥 𝘴𝘰𝘶𝘳𝘤𝘦𝘴, not a filing. • 𝗥𝘂𝗻-𝗿𝗮𝘁𝗲 is an 𝘢𝘯𝘯𝘶𝘢𝘭𝘪𝘴𝘦𝘥 𝘦𝘴𝘵𝘪𝘮𝘢𝘵𝘦, not money already earned. • 𝗔𝗻𝗮𝗹𝘆𝘀𝘁𝘀 𝗮𝗿𝗲 𝗳𝗮𝗿 𝗮𝗽𝗮𝗿𝘁. Morningstar's bear case is $25 a share, its base case $92, its bull case $188. • 𝗧𝗵𝗲 𝗺𝗮𝗿𝗸𝗲𝘁 𝗶𝘀 𝗷𝘂𝗺𝗽𝘆. The FT says the listing comes days after a $3.2tn tech sell-off, and that the hope a few weeks ago was $2tn. 𝘈 𝘤𝘰𝘮𝘱𝘢𝘯𝘺 𝘸𝘪𝘵𝘩 $17𝘣𝘯 𝘪𝘯 𝘲𝘶𝘢𝘳𝘵𝘦𝘳𝘭𝘺 𝘴𝘢𝘭𝘦𝘴 𝘪𝘴 𝘢𝘴𝘬𝘪𝘯𝘨 𝘵𝘩𝘦 𝘮𝘢𝘳𝘬𝘦𝘵 𝘵𝘰 𝘧𝘶𝘯𝘥 $900𝘣𝘯 𝘰𝘧 𝘱𝘳𝘰𝘮𝘪𝘴𝘦𝘴. 𝘕𝘦𝘹𝘵 𝘸𝘦𝘦𝘬 𝘵𝘩𝘦 𝘮𝘢𝘳𝘬𝘦𝘵 𝘯𝘢𝘮𝘦𝘴 𝘪𝘵𝘴 𝘱𝘳𝘪𝘤𝘦. Links in reply 👇

Private data in Claude? Do not start with the delete button. Start here Suppose you want to delete personal data from Claude. A work file you uploaded by mistake. A screenshot with private details in it. You want it gone, so it never ends up in Anthropic's training data. So you open Settings, find the file and press the bin icon. Done. You think you know what you are doing. 𝗬𝗼𝘂 𝗺𝗶𝗴𝗵𝘁 𝗯𝗲 𝘄𝗿𝗼𝗻𝗴. Here is the full story. 𝗪𝗵𝗮𝘁 𝘁𝗵𝗲 𝗯𝗶𝗻 𝗶𝗰𝗼𝗻 𝗿𝗲𝗮𝗹𝗹𝘆 𝗱𝗼𝗲𝘀 Settings > Privacy > Uploaded files > Manage lists every file you have uploaded. Read the notice at the top of that screen: "Deleting a file removes it from storage. Text already extracted into a chat isn't removed. To fully remove it, delete the chat." So the file goes. The text Claude read from it stays in the chat. I checked Anthropic's own pages to see what happens to that text. 𝗧𝘄𝗼 𝘁𝗵𝗶𝗻𝗴𝘀 𝗱𝗼 𝘁𝗵𝗲 𝗷𝗼𝗯 𝗽𝗿𝗼𝗽𝗲𝗿𝗹𝘆. Pressing the bin icon is neither of them. 𝟭. 𝗧𝘂𝗿𝗻 𝗼𝗳𝗳 𝘁𝗵𝗲 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝘁𝗼𝗴𝗴𝗹𝗲 On the same Privacy screen: "Help improve our AI models". With it off, Anthropic says it "will not use your previous or new chats or coding sessions for future model training." That covers the whole chat, including text from your files. One switch, every chat, old and new. With it on, training data "includes the entire related conversation, along with any content." Deleting only the file changes nothing. 𝟮. 𝗗𝗲𝗹𝗲𝘁𝗲 𝘁𝗵𝗲 𝗰𝗵𝗮𝘁, 𝗻𝗼𝘁 𝗷𝘂𝘀𝘁 𝘁𝗵𝗲 𝗳𝗶𝗹𝗲 Anthropic says: "if you delete a chat from your chat history, it will not be used to train future models." A deleted chat leaves your history at once and Anthropic's back-end storage within 𝟯𝟬 𝗱𝗮𝘆𝘀. Then press the bin icon too, so the stored file goes as well. 𝗧𝗵𝗲 𝗹𝗲𝘀𝘀 𝗰𝗼𝗺𝗳𝗼𝗿𝘁𝗮𝗯𝗹𝗲 𝗽𝗮𝗿𝘁𝘀 𝟭. 𝗡𝗼𝘁𝗵𝗶𝗻𝗴 𝗶𝘀 𝘂𝗻𝗱𝗼𝗻𝗲. "Your data will still be included in model training runs that are already in progress, or in models that have been trained." 𝟮. 𝗧𝗵𝗲 𝘁𝗼𝗴𝗴𝗹𝗲 𝗵𝗮𝘀 𝗲𝘅𝗰𝗲𝗽𝘁𝗶𝗼𝗻𝘀. The Privacy Policy says that even if you opt out, chats "flagged for safety review" are still used for model improvement. 𝟯. 𝗧𝗵𝘂𝗺𝗯𝘀 𝘂𝗽 𝗼𝗿 𝗱𝗼𝘄𝗻 𝘀𝗲𝗻𝗱𝘀 𝘁𝗵𝗲 𝘄𝗵𝗼𝗹𝗲 𝗰𝗵𝗮𝘁. It is stored "for up to 5 years" and may be used to train models, whatever the toggle says. 𝟰. 𝗧𝗼𝗴𝗴𝗹𝗲 𝗼𝗻 𝗺𝗲𝗮𝗻𝘀 𝗹𝗼𝗻𝗴𝗲𝗿 𝘀𝘁𝗼𝗿𝗮𝗴𝗲. Up to 𝟱 𝘆𝗲𝗮𝗿𝘀 in training pipelines, in de-identified form. Toggle off keeps you on the 𝟯𝟬-𝗱𝗮𝘆 period. 𝟱. 𝗙𝗹𝗮𝗴𝗴𝗲𝗱 𝗰𝗵𝗮𝘁𝘀 𝗮𝗿𝗲 𝗸𝗲𝗽𝘁 𝗹𝗼𝗻𝗴𝗲𝗿. Up to 𝟮 𝘆𝗲𝗮𝗿𝘀 if a chat is flagged as breaking the Usage Policy. 𝗪𝗵𝗮𝘁 𝘁𝗵𝗲 𝗱𝗼𝗰𝘀 𝗱𝗼 𝗻𝗼𝘁 𝘀𝗮𝘆 I could not find any Anthropic help page about the Uploaded files screen. The only wording is the notice inside the app. And for people with the toggle on: the docs say a deleted chat will not train future models. They do not say in plain words whether the copy already sitting in the 5-year training pipeline is erased too. 𝗦𝗼 𝘄𝗵𝗮𝘁 𝘀𝗵𝗼𝘂𝗹𝗱 𝘆𝗼𝘂 𝗱𝗼? The toggle decides training. Deleting the chat removes storage. 𝗗𝗼 𝗯𝗼𝘁𝗵. 𝗧𝗼𝗴𝗴𝗹𝗲 𝗳𝗶𝗿𝘀𝘁. If the toggle was already off, your file text was not headed for training anyway. Deleting the chat still clears it from storage. This toggle is for Free, Pro and Max accounts. Anthropic says it does not apply to Team, Enterprise or API use. ========================================= DO THIS (where to click) ========================================= 1. Open claude.ai. Click your name, then Settings, then Privacy. 2. Under Preferences, find "Help improve our AI models". Switch it off.This is the step that covers training for all your chats, old and new. 3. On the same screen, under "Your data", click Manage next to "Uploaded files". 4. For each sensitive file, look at the Location column. If it says "1 chat", click "Open chat 1" to see which chat holds the text. 5. Delete that chat. This is what removes the extracted text. Anthropic says a deleted chat is removed from your history at once and from its back-end storage within 30 days. 6. Then press the bin icon to delete the stored file as well. 7. Do not press thumbs up or thumbs down on a chat that holds sensitive content. That sends the whole chat as feedback, kept for up to 5 years. 8. For one-off sensitive work, use an Incognito chat. Anthropic says these are not used to improve Claude even when the toggle is on. Sources and screenshots in the reply.

Someone built a full desktop app to stop Claude accounts getting banned. Claude Cage runs Claude Code inside a small Linux machine on your computer and sends its traffic through your own proxy. It also sets the timezone and language to match the proxy. The main README is in Chinese, and China is not on Anthropic's supported list. The author writes that they are fed up with fingerprint browsers and the fear of bans. Its first releases came in early November 2026. It already has around 1,800 GitHub stars. To me that shows how much people outside Anthropic's supported list want Claude.. There is a Pashto README too. I speak Pashto, so I checked because Pashto is spoken in Pakistan as well as in Afghanistan but turned out Pakistan is on the list. Afghanistan is not. Using it from an unsupported country breaks Anthropic's Supported Regions Policy. The README admits its checks cannot promise your account stays safe. Where I live Claude just works, so the proxy does nothing for me. The sandbox is the useful part. The agent only sees the folders you open. Links in replies 👇👇 Repo: github.com/Lee-xeo/Claude-Ca…