HN user

juanpabloaj

333 karma

http://juanpabloaj.com/

https://twitter.com/juanpabloaj

Posts95
Comments73
View on HN
www.youtube.com 1mo ago

Kelsey Hightower: Kubernetes and retiring at the top [video]

juanpabloaj
11pts0
medium.com 2mo ago

Building an Online Taxi App Like Uber with Golang – Part 1, Nearby Taxis

juanpabloaj
4pts1
juanpabloaj.com 2mo ago

Show HN: Gemini free tier is all you need

juanpabloaj
8pts0
juanpabloaj.com 3mo ago

Show HN: A lightweight way to make agents talk without paying for API usage

juanpabloaj
58pts12
github.com 3mo ago

Show HN: Yeah Another Htop for Agents

juanpabloaj
1pts0
www.dandoescode.com 3mo ago

Building a Custom Claude Code Statusline

juanpabloaj
2pts0
github.com 3mo ago

Show HN: Hacker News comments summary to telegram

juanpabloaj
2pts0
blog.autorouting.com 3mo ago

Caching algorithms without knowing how they work

juanpabloaj
2pts1
news.ycombinator.com 4mo ago

Ask HN: What Are You Reading? (Mar 2026)

juanpabloaj
2pts2
juanpabloaj.com 4mo ago

Show HN: From Agentic Reasoning to Deterministic Scripts

juanpabloaj
1pts0
juanpabloaj.com 4mo ago

Show HN: The Silent Filter, The Delegation of Synthesis and Linguistic Drift

juanpabloaj
10pts0
news.ycombinator.com 5mo ago

SpaceX-xAI Merger: Nobody's Talking About the von Neumann Elephant in the Room

juanpabloaj
1pts4
adventures.nodeland.dev 5mo ago

The Future of the Software Engineering Career

juanpabloaj
2pts0
gist.github.com 6mo ago

Show HN: Obsidian Workflows with Gemini: Inbox Processing and Task Review

juanpabloaj
15pts6
juanpabloaj.com 9mo ago

Show HN: Life as an Accelerator of Chaos

juanpabloaj
1pts0
juanpabloaj.substack.com 10mo ago

Show HN: Context, Hallucinations, and How LLMs Are Changing Development

juanpabloaj
1pts0
github.com 2y ago

Show HN: Notifications for Jobs on Hacker News with Elixir and Telegram

juanpabloaj
2pts0
juanpabloaj.com 2y ago

Show HN: Distributing Elixir Applications with Burrito

juanpabloaj
2pts0
juanpabloaj.com 2y ago

Show HN: How to Use SQLite3 with Elixir and Ecto

juanpabloaj
4pts0
github.com 3y ago

SwissGL is a minimalistic wrapper on top of WebGL2 JavaScript API

juanpabloaj
1pts0
medium.com 5y ago

Distribution Visualizations for Data Science

juanpabloaj
1pts0
github.com 5y ago

Show HN: 1D cellular automata with dynamic exchange of rules

juanpabloaj
1pts0
www.youtube.com 5y ago

The Year's Biggest Breakthroughs in Math and Computer Science

juanpabloaj
3pts0
grist.org 5y ago

Soap on tap? A startup arrives in NYC with a plan to take the plastic out

juanpabloaj
1pts0
github.com 5y ago

A free video streaming service that runs on a ESP32

juanpabloaj
352pts48
www.freecodecamp.org 6y ago

Never ever run directly against Node.js in production. Maybe

juanpabloaj
2pts1
bestchai.bitbucket.io 6y ago

ShiViz: Graphs from dis­tri­but­ed sys­tem exe­cut­ion logs

juanpabloaj
1pts0
github.com 6y ago

Anomaly detection related books, papers, videos, and toolboxes

juanpabloaj
2pts0
github.com 7y ago

Lightweight Kubernetes. 5 less than k8s

juanpabloaj
1pts0
github.com 7y ago

A Flexible Developer Tool That Runs Processes and Responds to Filesystem Changes

juanpabloaj
2pts0
Take better notes, by hand 4 months ago

I love to use a paper notebook for fast notes, random thoughts, and to capture tasks (something similar to a GTD inbox). With it, I use a small system of symbols (some degree of similarity with the bullet journal method).

The only issue with paper is the edition. My solution has been to use a compact, slim ring binder with a notebook-like feel. If required, you can move sheets to reorganize content, move the most important ones to another place, etc. Until now, the best alternative that I have found is the Kokuyo Campus Smart Ring Binder.

0ThreadHN
Ask HN: What Are You Working On? (March 2026) 5 months ago

No practical code example, sorry. The post is based on my own experience using agents, and I haven't reached a reusable generalization yet.

That said, two cases where I noticed the pattern:

Meal planning: I had a weekly ChatGPT task that suggested dinner options based on nutritional constraints and generated a shopping list (e.g. two dinners with 100g of chicken -> buy 200g). After a few iterations, it became clear that with a fixed set of recipes and their ingredients, a simple script generating combinations was enough. The agent's reasoning had already done its job — it helped me understand the problem well enough to replace itself.

QA exploration: I was using an agent to explore a web app as a QA tester. It took several minutes per run. After some iterations, the more practical path was having it log its explorations to a file, then derive automated tests from that log. The agent still runs occasionally, but the tests run frequently and cheaply.

Regarding your point about tasks that need individual reasoning every time — I think you're right, and that's actually the core of the idea. Not every task matures into a script. Extracting structured data from images probably stays deliberative if the images vary significantly. The cycle only applies to tasks that, after enough repetitions, reveal a stable pattern. The agent itself is what helps you discover whether that pattern exists.

0ThreadHN
Ask HN: What Are You Working On? (March 2026) 5 months ago

These past weeks I finally organized some ideas I'd been sitting on and wrote two posts:

From Agentic Reasoning to Deterministic Scripts: on why AI agents shouldn't reason from scratch on every repeated task, and how execution history could compile into deterministic automations

https://juanpabloaj.com/2026/03/08/from-agentic-reasoning-to...

The silent filter: on cognitive erosion as a quieter, more probable civilizational risk than a catastrophic event

https://juanpabloaj.com/2026/02/27/the-silent-filter/

0ThreadHN
Cognitive Debt: When Velocity Exceeds Comprehension 5 months ago

The second is absorption: mental models form, edge cases become intuitive, architectural relationships solidify into understanding. ... . The friction of implementation creates space for reasoning.

This gap between output velocity and comprehension velocity is cognitive debt.

I have felt that lack of absorption during the last months, adding doomscroolling to the equation, I have felt how my thinking is disappearing.

I tried to speculatively expand that idea in this post

https://news.ycombinator.com/item?id=47186004

0ThreadHN
Show HN: Obsidian Workflows with Gemini: Inbox Processing and Task Review 6 months ago

If that is the question,

I agree, the LLM support we lose some level of manual work, maybe that is useful to be more familiar with the information, although I am not sure if that is a critical step. The LLM gives us management support. We can use a command to collect incomplete tasks, the LLM is doing that with extra steps, and it shows us the collected information, but in the end, we decide which tasks to prioritize.

0ThreadHN
Show HN: Obsidian Workflows with Gemini: Inbox Processing and Task Review 6 months ago

Inbox Processing Workflow - GTD-style system to keep your inbox at zero, with AI classification of notes to projects, resources, or someday/maybe lists.

Incomplete Tasks Review Workflow - weekly review that analyzes your tasks, identifies gaps, detects duplicates, and generates a focused "plan of attack" with your highest-priority actions.

Both workflows combine classic productivity principles (GTD, weekly reviews) with AI assistance to reduce cognitive load and maintain system trust. They use command-line tools (find, ripgrep) to analyze your vault and generate processing recommendations in an easy-to-review card format.

Use at your own risk. Validate each command before executing it. It is strongly recommended to use a version control system (Git) in your Obsidian vault to visualize and revert changes made by the agent.

Any suggestions to improve these workflows are appreciated.

0ThreadHN