David Gasquez
LightNews LightNews
banner
davidgasquez.com
David Gasquez
@davidgasquez.com
5.2K followers 1.2K following 1K posts
Data @ Protocol Labs.

Open Data, Open Source, Open Protocols.

Walks taker. Progressive Metal enjoyer.

davidgasquez.com
Posts Replies Media Videos
Reposted by David Gasquez
davidgasquez.com
Half baked idea and proof of concept but at least it is out there.

I wrote about Tributary, a credibly neutral mechanism to incentivize and elicit useful datasets.

davidgasquez.com/tributary-da...

I worked on it 6 months ago at a research retreat (IERR 2025) but never wrote about it.
Text of the blog post
February 11, 2026 at 6:51 PM
davidgasquez.com
Half baked idea and proof of concept but at least it is out there.

I wrote about Tributary, a credibly neutral mechanism to incentivize and elicit useful datasets.

davidgasquez.com/tributary-da...

I worked on it 6 months ago at a research retreat (IERR 2025) but never wrote about it.
Text of the blog post
February 11, 2026 at 6:51 PM
Reposted by David Gasquez
davidgasquez.com
Also made a cute embedding of all their products!

datania.github.io/mercadona-ca...
embedding of all mercadonas
February 10, 2026 at 9:54 PM
davidgasquez.com
Also made a cute embedding of all their products!

datania.github.io/mercadona-ca...
embedding of all mercadonas
February 10, 2026 at 9:54 PM
davidgasquez.com
Discovered Mercadona's API and wrote a quick scrapper that will run weekly and dumps everything into JSONs in HuggingFace.

Useful to track prices over time, check new arrivals, ...

Data. huggingface.co/datasets/dat...

Code. github.com/datania/merc...
fiiles
February 10, 2026 at 9:53 PM
davidgasquez.com
The team that built CXDB recently published their take on "software factories". Recommended reading as it contains a few cool tricks (e.g. holdout sets, ...).

factory.strongdm.ai
February 9, 2026 at 8:56 AM
davidgasquez.com
Spotted this interesting design/implementation of a self-hosted context store for agents.

- Turn DAG
- Blob Deduplication / Content Addresses Storage
- BLAKE3
- Dynamic types, visual debugging, ...

github.com/strongdm/cxdb
CXDB - AI Context Store CXDB is an AI Context Store for agents and LLMs, providing fast, branch-friendly storage for conversation histories and tool outputs with content-addressed deduplication. Built on a Turn DAG + Blob CAS architecture, CXDB gives you: Branch-from-any-turn: Fork conversations at any point without copying history Fast append: Optimized for the 99% case - appending new turns Content deduplication: Identical payloads stored once via BLAKE3 hashing Type-safe projections: Msgpack storage with typed JSON views for UIs Built-in UI: React frontend with turn visualization and custom renderers
February 9, 2026 at 8:51 AM
Reposted by David Gasquez
sqs7.bsky.social
If you are curious what a frontier coding agent feels like to use, and don't want to pay or put in a credit card to try it out, here you go:

ampcode.com/code/AMP-BSK...
Redeem on Amp →
Redeem this offer on Amp, the frontier coding agent.
ampcode.com
February 7, 2026 at 12:58 AM
Reposted by David Gasquez
gordon.bsky.social
Why is the AI revolution happening on the command line first? Because the terminal is still the most open-ended general-purpose computing platform available.

Unix Philosophy is All You Need.
gordon.bsky.social Gordon @gordon.bsky.social · 10d
there has never been a better time to get terminal-pilled
gordon.bsky.social Gordon @gordon.bsky.social · 11d
File system wins. The combination of agents + plain text data + file system is almost too powerful.
February 7, 2026 at 7:28 AM
Reposted by David Gasquez
nimobeeren.com
Yeah, like please invest that effort into turning your app state into local Markdown and JSON (or SQLite) files so I can use my good AI tools to work with it
cpaxton.bsky.social Chris Paxton @cpaxton.bsky.social · 12d
i wish all these random programs would stop adding AI assistants. not because AI is bad, but because these programs are bad and i don't want them implementing ai. like adobe acrobat. come on.
February 3, 2026 at 5:09 PM
Reposted by David Gasquez
davidgasquez.com
Wrote about "Barefoot Data Platforms", my take on minimal and agent friendly data platforms!

davidgasquez.com/barefoot-dat...
So, how does a minimal and opinionated data platform look like? Minimalism for me here means low abstraction and no frameworks. You write your scripts. These scripts are assets, and these assets depend on each other 1. That’s it. The opinion side of things is the interesting part. Here are the key ideas of the Barefoot Data Platform I built: Classic functional, declarative, independent, composable, and idempotent transformations Co-located assets, metadata, and documentation so assets have everything needed to be understood and reproduced in the same file One storage layer. DuckDB or SQLite, Parquet files, or whatever you want as long as you define a materialize function Many automated checks (ruff with all the rules enabled, ty, data tests, prek hooks, custom bdp check, …) for the agents
February 3, 2026 at 10:49 AM
Reposted by David Gasquez
orta.io
Want to re-raise this banger of an article, which really helped frame the differences between atproto and bluesky, and turned me into a convert for atproto

bsky.app/profile/dana...
February 3, 2026 at 11:14 AM
davidgasquez.com
Wrote about "Barefoot Data Platforms", my take on minimal and agent friendly data platforms!

davidgasquez.com/barefoot-dat...
So, how does a minimal and opinionated data platform look like? Minimalism for me here means low abstraction and no frameworks. You write your scripts. These scripts are assets, and these assets depend on each other 1. That’s it. The opinion side of things is the interesting part. Here are the key ideas of the Barefoot Data Platform I built: Classic functional, declarative, independent, composable, and idempotent transformations Co-located assets, metadata, and documentation so assets have everything needed to be understood and reproduced in the same file One storage layer. DuckDB or SQLite, Parquet files, or whatever you want as long as you define a materialize function Many automated checks (ruff with all the rules enabled, ty, data tests, prek hooks, custom bdp check, …) for the agents
February 3, 2026 at 10:49 AM
davidgasquez.com
Best clanker out there!
January 31, 2026 at 7:23 PM
davidgasquez.com
TIL you can install Python tools without uv or Python with a single curl command!

uvx.sh

Useful for Docker, CI pipelines, or anywhere you don't want to mess with the Python installation or venvs!
uvx.sh Install Python tools with a single command. Powered by uv. For example, to install ruff:
January 24, 2026 at 10:36 PM
Reposted by David Gasquez
ssp.sh
It's amazing how many declarative data stacks have emerged since I started this topic.

I just updated the list with the latest open-source once. Do you know of any others? Happy to append to the list.

Check out the full breakdown at .
Image from X
January 23, 2026 at 8:10 AM
Reposted by David Gasquez
patak.dev
someone from github should write a check to tangled and merge it into main
anirudh.fi Anirudh Oppiliappan @anirudh.fi · 25d
i absolutely love our new code review page! it's orders of magnituted nicer being able to look at the diff while you author your review comments.
January 21, 2026 at 3:55 PM
davidgasquez.com
Realized I haven't used Jupyter Notebooks in a good while. Codex/CC with PEP 723 inline metadata knowledge has been doing it for myself.
January 21, 2026 at 12:38 PM
Reposted by David Gasquez
lukesteuber.com
Data visualization: Every human language, from modern day back through protolanguage to a hypothetical common origin. Accurate, sourced, possibly complete. Includes sign language!

Tap or mouse over to highlight individual branches; many also have more info.

🛌 this project has been a beast
Networking
7,370 languages visualized as a force-directed network
dr.eamer.dev
January 21, 2026 at 5:14 AM
Reposted by David Gasquez
mitsuhiko.at
Weekend thoughts on Gas Town, Beads, slop AI browsers, and AI-generated PRs flooding overwhelmed maintainers. I don't think we're ready for our new powers we're wielding. lucumr.pocoo.org/2026/1/18/ag...
Agent Psychosis: Are We Going Insane?
What’s going on with the AI builder community right now?
lucumr.pocoo.org
January 18, 2026 at 10:38 AM
Reposted by David Gasquez
danabra.mov
formats over apps
A Social Filesystem — overreacted
Formats over apps.
overreacted.io
January 18, 2026 at 7:05 AM
davidgasquez.com
Shared an assortment of personal workflows I've found useful when working with "agents" across work, data, and research.

In 2025, I had ton of fun tinkering with this new way of working. I'm sure they won't last until next year.

Meanwhile, hope they're helpful!

davidgasquez.com/useful-agent...
davidgasquez.com David Gasquez @davidgasquez.com · Dec 23
Thanks for sharing! Love seeing how other folks work and was very curious about your workflows specifically.

You are doing many interesting things, please keep sharing! 🙌
December 23, 2025 at 8:11 PM
davidgasquez.com
Updated the design of my personal website and I love it!

davidgasquez.com/handbook
Company Knowledge Management All Organizations produce some kind of knowledge. If not properly managed, it’ll lie on your ex-employees, oral history and tribal knowledge. If we think about a company as an organism, then a knowledge management system is essentially the (collective) brain that keeps that organism alive and running. A corporate knowledge management system, ideally, contains every single bit of codifiable information within the company resulting in a library of all projects, processes and procedures. Managing an organization’s knowledge is mainly a people problem, not a technology problem. If the Culture is not properly set up, no one will do it and no amount of technology is going to help you magic it out of the ether. --- All monospace.
December 19, 2025 at 9:31 AM
Reposted by David Gasquez
simonwillison.net
At the risk of starting the flame war to end all flame wars...

Modern LLMs (GPT-5.1, Claude 4.5, Gemini 3) produce excellent code and can be a significant productivity boost to software engineers who take the time to learn how to effectively apply them - especially if used with coding agent tools
November 27, 2025 at 7:55 PM
davidgasquez.com
Been using Codex CLI for some tasks like tagging and entity extraction.

Turns out tasks get way easier when you force more small, local decisions without global context and then a few "aggregations" on top.

Accidentally rediscovered MapReduce again! 😅
davidgasquez.com David Gasquez @davidgasquez.com · Oct 22
I've been using this pattern to "specialize" Codex for vaguely defined tasks like classification, filtering, soft sorting, ...

davidgasquez.com/specializing...

Made more than 10,000 invocations so far (reusing my ChatGPT subsciption) and am really happy with the pattern!
’ve been using Claude Code to take care of scrappy data cleaning tasks for a while. These days though, I’m using Codex as my coding agent. Similar to what I did with Claude, I’ve been “fine-tuning” Codex CLI to work on a few different vaguely defined tasks like classification, voting, filtering, or ranking. The pattern in this post works surprisingly well when you have the following conditions: Loosely defined open-ended tasks. e.g., tagging tweets with a set of predefined labels, extracting structured information from a GitHub issue, … Powerful agentic capabilities. Doing the task requires something more than a simple llm call or PydanticAI script. e.g., using gh api CLI to get the number of stars of a repository. Structured outputs. You need a response in a certain shape! This is something codex exec can do that claude couldn’t and is really powerful. e.g., return exactly True or False and nothing else. Save money! Unlike llm or other tools/libraries that require an OPENAI_API_KEY, Codex can use your ChatGPT subscription, making things “free”.
November 22, 2025 at 10:31 AM