These sponsors are hiring: @mesa_dot_dev: a Senior Systems Engineer in SF or remote in the US, building a new GitHub. mesadev.notion.site/Senior-S… @Railway: a Senior Infra Engineer to work on filesystems and storage, remote anywhere. railway.com/careers/platform… Chat with them!

Love this article - Satya talks about building "token capital" - or organisational learning to turn workflows and tasks into AI systems and loops. Why doesn't it exist today? This is (and will be) an unsolved problem - requiring great research, infrastructure AND product work. also what we're doing at @supermemory right now. (I personally have been working on this problem for years now!) and i'm glad people are talking about it now! 1/ Research No one knows the right "winning" architecture to build something like this. There is no right answer. There are no deterministic good benchmarks. for the AI system has to learn and improve over time - It has to have an understanding of time, how the world evolves and connect the dots just like humans do. It would have to infer or "reason" through knowledge. It has to forget things as well. This article talked about building evals specific to your org - We believe this is the right way! We have been building a framework to easily evaluate systems on any setup (Git.new/membench) and also a dataset for long horizon organizational data (smfs.ai/research). A lot of our customers have set up evals that matter to them. It does not matter if it's graph vector etc - customers don't care. This system should be composable to whatever use case the enterprise wants, and something they can build on / amend. 2/ Infrastructure It's not just about having a huge vector store. Every raw document / item can amount to hundreds or thousands of interconnected knowledge, that's also being dreamt on and new knowledge being evolved from it. The model that actually makes the learning also can't be too expensive. it can't even be 50% of the main model! Because this model will be looking at everything and choosing what to learn. So there's also a lot of distillation / inference engineering involved there. At @supermemory we solve these by building our own data systems and a model that is doing the learnings. We have a fact based temporal graph that also ensures that everything is properly attributed and traceable. 3/ Product For people building on top of supermemory, we have to make it completely hackable and composable for every use case. Complex organizations have different permissions structures - And different data sources to learn from. Different things to learn. They also have different ways of bringing it back to the agent - Sometime it will be "implicitly" given, or the agent may "explicitly" look up data. Maybe you want to give that data as @karpathy LLM wiki (filesystems) style! For this we have built all permission system and controls into supermemory. It's natively multi tenant, and queryable deterministically (as SQL) at the same time. You can also use it as a filesystem! We bring the knowledge as needed to the agent . We call it SMFS.ai ------ We are trying to build the best memory and context system for AI so that organizations can build their own token capital! This is a hard unsolved problem and an important one to solve.

Intelligence is now being commodified via LLMs the only missing part is biodata vault LLMs interoperability. We provide both via NFT gated filesystems from Sequencing Labs. biofs.genobank.io/

🐧 Day 12/30 — #Linux Storage management is a fundamental skill for every Linux administrator. Before a disk can store data, it must be partitioned, formatted with a filesystem, and mounted into the Linux directory structure. Linux Disk Management – Partitioning, Formatting, and Mounting Understanding how Linux handles disks helps you manage storage efficiently and avoid data-related issues on servers and workstations. Key Disk Management Concepts: → Partitioning → Formatting → Mounting Partitioning Disks A partition is a logical section of a physical disk. Partitioning allows a single disk to be divided into multiple independent storage areas. Common tools: → fdisk → parted → lsblk Example: → sudo fdisk /dev/sdb Opens the partition manager for a disk. Viewing Available Disks → lsblk Displays all connected storage devices and partitions. → df -h Shows mounted filesystems and available disk space in a human-readable format. Formatting Partitions After creating a partition, it must be formatted with a filesystem. Common Linux filesystems: → ext4 → xfs → btrfs Example: → sudo mkfs.ext4 /dev/sdb1 Formats the partition using the ext4 filesystem. Mounting Filesystems Linux accesses storage through mount points. A partition must be mounted before it can be used. Example: → sudo mount /dev/sdb1 /mnt/data Makes the partition accessible through the /mnt/data directory. Viewing Mounted Filesystems → mount Lists currently mounted filesystems. → df -h Displays mounted storage and available space. Persistent Mounting To automatically mount a partition during boot, administrators configure: → /etc/fstab This file defines permanent mount settings for disks and partitions. Why Disk Management Matters: → Add new storage to Linux servers → Manage application and database data → Monitor disk usage effectively → Prevent storage-related outages → Configure reliable production environments Mastering partitioning, formatting, and mounting is an essential step toward becoming a skilled Linux administrator, DevOps engineer, or cloud engineer. 🐧 Grab Linux Ebook: codewithdhanian.gumroad.com/… #Linux #LinuxTutorial #DiskManagement #LinuxCommands #SystemAdministration #DevOps #CloudComputing #OpenSource #Storage #100DaysOfCode

processes and filesystems. This is why they're lightweight — no guest OS overhead, no gigabytes of RAM wasted on redundant system processes.","A container image is your compiled artifact. You build it once, run it anywhere. No more SSH-ing into servers to

Your S3 bucket is just an expensive filesystem pretending to be an object store. ZeroFS flips it: serve S3 buckets as POSIX filesystems over NFS and 9P: - Compresses and encrypts everything before upload - Raw block devices over NBD, in the same process github.com/Barre/ZeroFS

Linux 101: Drives, Partitions, and Mounts Practice partitioning drives, formatting them with different filesystems, and working with mounts in a series of hands-on challenges: - Mount a drive with existing data and read its contents labs.iximiuz.com/challenges/… - Create a GUID Partition Table (GPT) on a blank drive labs.iximiuz.com/challenges/… - Split a drive into multiple partitions and format them as ext4 and btrfs labs.iximiuz.com/challenges/… - Mount an existing directory at a new location (bind mount) labs.iximiuz.com/challenges/… - Make a filesystem mount survive a reboot labs.iximiuz.com/challenges/…

Agent Harness is just a hype or an improvement? Tomorrow 14 Jun, 10 AM IST on kmeanskaran.substack.com Explaining different components of Agent Harness over Classic AI agents like: Planning ➝ Backends and Virtual Filesystems ➝ Context Engineering ➝ Subagents ➝ Memory ➝ Skills ➝ Sandboxes ➝ Human-in-the-loop ➝ Tools This is an introductory article up next, I am building a one end to end agent harness using @LangChain DeepAgents with complete architecture and deployment on @Railway CI/CD Stay tune!

a professor at Illinois got frustrated with existing systems programming textbooks so he started a wikibook project and had students help write it it covers C, processes, threads, synchronization, memory allocation, networking, filesystems, scheduling and security

internals, overlay filesystems, and networking modes. You need exactly three commands: docker build, docker run, docker push. Everything else is optimization you learn when something breaks.