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...

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...

Updated the design of my personal website and I love it! davidgasquez.com/handbook

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

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! 😅

the two types of organizations: spreadsheets and cults

Awesome job with this new series @jed.co! Love the topics and conversations.

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!

I've been curating some "Agentic Coding" tips and tricks for a while. Check them out if you're into that! davidgasquez.com/handbook/art...

I've become one of those people who run multiple coding agents at once - here are my notes on embracing the parallel coding agent lifestyle simonwillison.net/2025/Oct/5/p...

When you try to predict about the impact of AI tools on software engineering - a great analogy I heard from @simonwillison.net is to look at the impact of smartphones (+ the amazing cameras they have) on filmmaking. Noticed that those able to shoot pro films using a smartphone are... pros?

I personally see collapse as an inevitability for every individual institution. Nothing lasts forever. The smart way to build systems is to enable reforms so that they can adjust to reality without destroying what works in the process. This is pretty baked into the philosophy of Bluesky

if only there were a decentralized, immutable, and versioned way to fix this!

I wrote up some thoughts about why we’re seeing a gap in AI tool use among different types of developers narphorium.com/blog/top-dow... 1/4

Is there a name for the pattern where you try building the same thing (feature, project, ...) a bunch of times with different agents to get a sense of the implementation design space? I usually run things at least 2 or 3 times until I "feel" what is the way I want it to be built.

Both Evidence and Observable Framework seem to be slowing down in development. - github.com/observablehq... - github.com/evidence-dev... Not sure why. Anyone has any context or ideas?

My dotfiles repository is now mirrored on @tangled.sh too! tangled.sh/@davidgasque...

Spent some time refining the approach and benchmarking it. Just published a blog post about the core idea. Can a bunch of LLM Agents be used to rank an arbitrary set of items in a consistent way? 🤖 davidgasquez.com/ranking-with...

Wrote a post about a small pattern I've been using for a while. Replacing chunks of bash scripts with `llm` or inline Claude Code calls. For example, for data cleaning/structuring. davidgasquez.com/scrappy-data...

usually the baseline is “nothing” so the right heuristic is usually not “is it ideal” but rather “is it better than nothing?”

Are there any benchmarks/evals that track model performance over time? I've heard things like Claude/Cursor getting dummier over time (haven't noticed much myself) and am wondering if there is some data to back this.

New data oriented file format just dropped. FastLanes, "like Parquet, but with 40% better compression and 40× faster decoding". 👀 Seems it can exploit correlations between columns and have fully SIMD friendly encodings to help with vectorization. github.com/cwida/FastLa...

Asked Claude to move my handbook notes from Obsdian to my Astro website. Very happy with the results! davidgasquez.com/handbook/dat... I'll keep the Obsidian Publish version around while I work on making it look as good.

Will 2025 finally be the year of the Linux desktop? Really cool to see folks like @mitsuhiko.at or @ssp.sh trying out Arch, Hyprland, and other modern Linux stuff thanks to Omarchy! More people, more polished experience, more dotfiles to learn from!

The end dataset also serves as a much smoother API! - No key required - Batch export friendly - Explorable in the browser

Spent some time this weekend playing with AEMET's APIs and wrote a small post sharing what I learned and how I approached the project. davidgasquez.com/exporting-ae... I'm really enjoying working on these small, one-off projects as a way to experiment with different techniques. 🧪

Updated linkweaver (custom notes & research helper) with a couple of new tricks. 1. Saves the URL content locally 2. Accepts any command to preprocess the generated Markdown. E.g: `llm "Clean the following Markdown"`. github.com/davidgasquez... Want to try it? `uvx linkweaver` and enjoy! 😀

One of the best things I'm using LLMs for is to make lots of small UNIX style CLIs! 🤩 I'm talking about simple/silly things like listing all the unique links in a bunch of markdown notes (`xl *.md`). What a time!

Seeing a new long form video from Michael (Vsauce) after so long made my day! 🤩 www.youtube.com/watch?v=xHd4...

I think all my projects now have a very simple CLAUDE.md file that imports the README, CONTRIBUTING, and, Makefile. Great setup for humans and for LLMs! davidgasquez.com/llm-friendly...

🏖️ Summer is around the corner, and I thought of making a summer special in the form of a Postcard Series. This edition holds unique & insightful links to read, listen to, or enjoy while chilling at the pool or when lying on the beach, presented as 14 postcards with 3 links and a description each.

Now making the agents in the tool chose the final name of the tool using the tool itself. 😜 github.com/davidgasquez...

One thing I took from this experiment is that now, almost all my notes have a few <resource> XML tags that are very helpful when "talking" with the note.

Just watched this great video and it was fun and all but the big take away is the last sentence "we don't know what is necessarily important but we know what we love, so work on that" youtu.be/x32Zq-XvID4?...

Finally had some time to publish a vibecoded tool I (and Claude Code) built to explore PydanticAI. Replicates a contest where jurors evaluate candidates in pairwise comparisons that get turned into a leaderboard. github.com/davidgasquez...

Glad to see more projects adopting the @file.md imports in Markdown. docs.anthropic.com/en/docs/clau... Alongside [[Wikilinks]], they are my top used not-so-standard features!

Spent some time going through @cameron.pfiffer.org 's Comind project and @void.comind.network public code and had a lot of fun learning about them! - comind.stream - tangled.sh/@cameron.pfi... Love Comind's components idea! Clean and simple.

Anyone running any kind of workflows with the base Claude Code GitHub Action? Been thinking of doing some lightweight ones as cron jobs that result in small PRs. - Review documentation - Cleanup/connect/open issues - Iterate the CLAUDE.md file

Anyone running any kind of workflows with the base Claude Code GitHub Action? Been thinking of doing some lightweight ones as cron jobs that result in small PRs. - Review documentation - Cleanup/connect/open issues - Iterate the CLAUDE.md file

Still relevant and amazing talk by @bcantrill.bsky.social! Bringing the Unix Philosophy to Big Data. youtu.be/S0mviKhVmBI

Starting to do the same for datos.gob.es Data Catalog! huggingface.co/datasets/dat... Keeping the state of the data catalog at any point in time makes it easier to know what changed. Will be running this periodically and updating the Data Catalog JSONs.

Starting to do the same for datos.gob.es Data Catalog! huggingface.co/datasets/dat... Keeping the state of the data catalog at any point in time makes it easier to know what changed. Will be running this periodically and updating the Data Catalog JSONs.

Came across this awesome video again. Couldn't resist sharing it! TLDW: Voting is hard 😅 youtu.be/qf7ws2DF-zk

Wrote a post about some things I've been doing to make my projects more LLM friendly. Spoiler alert: it makes the projects more human friendly too! davidgasquez.com/llm-friendly... Any other ideas or suggestions?

Waiting for Claude Code to open a PR is the new “My code is compiling.” xkcd.com/303/

Loved this Public Goods Funding landscape by @harsimony.bsky.social! splittinginfinity.substack.com/p/the-public... So many rabbit holes to continue digging!

Vortex (extensible columnar file format) is now part of the Linux Foundation! 👀 github.com/vortex-data/...

File over app, by @stephango.com is always an amazing read! stephango.com/file-over-app

Ended up writting a small CLI that you can point to a Markdown note and get an "expanded" view into it. It reads all the links, makes them Markdown and returns all of them under different XML tags for your favorite LLM to consume! github.com/davidgasquez...

I've been using NotebookLM again for some research and has been an amazing experience. That said, with the large context some of the current LLMs have, wouldn't it be better to feed all the resources as Markdown files to the LLM? What is the state of RAG vs direct context loading?