I still believe that it is extremely important to learn to read and how to stay with long form books, to identify the canon, and to go through it. I may be a fossil.

Fable is super structural and methodical. The more abstraction you can handle - the more rewarding it gets.

i have seen enough proof now that using a coding agent is a deep skill it's confusing because the people you see heavily using them produce horrible results but that's because it's a skill! you can get better and the ceiling seems pretty high - this is very exciting to me

Opus 4.8 understands some really subtle nuances in UX and data modeling that makes it just plain lovely to work with. Still have to keep reminding myself that this is the dumbest it's ever going to be.

Congrats @tech_optimist @changhiskhan 💯 nailed it: → operational state → multimodal lakehouse → mutable context → versioned snapshots → time travel exactly why we're building Omnigraph on Lance Thanks for the mention!

Every Hermes release is like a full Apple presentation [from Apple's golden age I mean]

I use SaaS SaaS adds LLM chat Agents use SaaS via MCP Every SaaS ships native CLI ⬅️ We are here 💡SaaS is mostly a DB wrapper DB CLI is better than SaaS CLI Agents can do all the DB ops I can vibe-code UI myself I use database

shape of agent-native db is more clear now: less: system of record more: context assembly models, memories, maps, reasoning structures from "retrieve some data for LLM" to "curate & maintain context state" multi-paradigm, not just multimodal: graph, columnar, documents, KV, objects, embeddings not trying to suck every resource into acts as an index & coordination surface for agents & existing systems CONTEXT-AS-CODE git-style: branch, version, merge set of linted queries [lens] ready for concurrent batch writes ONTOLOGY-AS-CODE declarative schema file enforced, versioned, tracked SECURITY-AS-CODE single YAML policy file enforced at the lens level UI-AS-CODE Jupyter-like notebook dashboards living projection of the domain models INFRA-AS-CODE: lakehouse: compute & storage are separated terraformed: S3 elastic compute FROM source of truth TO source of competing views on what's useful now.

AI slop is good, actually. Slop is what enables fast parallel experimentation. The etiquette and skill is understanding the boundaries of where slop exists and the extent to which it should be cleaned up and how. A few examples: I’m working on the internals of some system right now. The API and GUI of this thing is fully zero shame slop. It’s horrible. But it lets me focus on the core quality while shipping a usable piece of alpha quality software to testers (transparent about the slop frontend). Similarly, this system has plugins. We sent agents in Ralph loops overnight to generate dozens of plugins. The plugins are slop. The quality is bad. The plugin API/SDK is absolutely not done. But we can test a full GUI with a full plugin ecosystem. When we change the API, we can regenerate them all. The cost of change is just tokens, the velocity is incomparable to before. I built Terraform. We tested and shipped TF 0.1 with about 3 very weak providers. Because we ran out of time. Building was slow. And when we changed our SDK the cost was immense. Totally different today, 10 years later. Today, I would’ve slop generated 100 providers (again, with transparency and cleanup later, but just to prove it out). As an anti example, I would not PR this (without prior warning) to another project. I would not throw this onto customers without full review or transparency (as I’m already doing). I would not accept first pass slop. It’s almost never right. Slop is a tool. And like anything else it’s not blanket bad or good. The context is everything.

Fully migrated to @zeddotdev for code docs I used to switch between VSCode <> Cursor <> Obsidian Now it’s just Zed Minimal. Opinionated. OSS. Tiny RAM footprint. Rust-native UI render on Metal beats Electron all the time. One of those upgrades when you don’t look back.

Quickest waitlist signup ever

Conjecture Institute Advisor @DavidDeutschOxf on some problems he'd like to see solved: 1. The theory of how to create an artificial intelligence (which will be far more illuminating than actually implementing the theory) 2. Progress in constructor theory (fundamental theory in physics that casts all laws of physics in terms of possible and impossible tasks) 3. Revival of optimism (apparent obstacles are just problems to be solved)

On-prem is the new cloud @chamath called this 2 months ago. Now it's everywhere: On-prem - ideal VPC - okay SaaS / public cloud - 👎 The cost of setting up infra is decreasing fast. Agents can configure anything in a matter of hours: Firmware, LAN, VMs, k8s, Terraform - you name it. Many companies are running open-source LLMs in-house for simple workflows. And pseudonymize data for cloud models. CFOs love it! They hate everything that is per-seat or per-token. Way more focus on what's defensible: data policies ontology know-hows decision chains New motto: Data sovereignty Zero vendor lock-in Headless OSS stack On-prem / hybrid infra Centralized governance Context graph ownership Bearish on rent Bullish on own

The reason I am an AI optimist is that the world is full of brilliant, driven, creative people Now these people - across science, medicine, technology, business and more - can create and iterate faster than ever before How could you not be hopeful?

this aged well

While others have been working diligently to destroy reading experiences using pretext, I’ve been thinking a bit about how to improve them using llms. Here’s a tldr concept where you can seamlessly swipe between synopsis and original article while maintaining your reading position at all times.

in the limit most startups converge to: ontology terraform config

It’s 2am again, my favourite time, and as always reality is still staring me in the face 🧐

Indexed Lenny's content for agents > ask any questions without recall issues (structure codegen) > converted all the markdown files to a db > connect curated data as context for agents via MCP, API, CLI > was set up in 10 min and can be applied to other knowledge bases!

Encoding the operational world requires a lot more than markdown files...