jjuliano

Found it - https://groups.google.com/g/rec.humor.funny/c/zNJ6doo3pTI/m/...

It's quite cheap at $10 at 1000 premium requests (1 request is like a plan mode + implementation + tests + commit & push). The only problem is I have already used it all, but was billed on the 3rd day of the month, and have to wait till next month to use it.

I remember I was a senior lead softeng of a worldbank funded startup project, and have deployed Ruby with jemalloc in prod. There's a huge noticeable speed and memory efficiency. It did saved us a lot of AWS costs, compare to just using normal Ruby. This was 8 years ago, why haven't projects adopt it yet as de facto.

I remember I traded my SNES console for a 9.6bps modem. Spent my high-school nights connecting to BBSs, door games, fidonet. Saw modem speed progressing to 28.8, 33.3 and finally 56k (and I'm still at 9.6k lol). And the joy of trying to use a winmodem on Linux. Those days are so nostalgic.

Why just join a local Kingdom Hall near you? People will genuinely love you there.

I did something similar back in 2019 but for learning Dutch with games, which I made originally for my child but this kinda helps me remember many A2 words and helps me with the exams. Now I have the Dutch citizenship.

Not as extensive as the site but with the images, interactions, it helps with remembering the vocabularies. https://play.google.com/store/apps/developer?id=Joel+Bryan+J...

I'm a solo founder, and this month, I just got into Cursor vide coding development (from Emacs). Still working and getting accustomed to this new vibe coding as it's easy to mess everything up.

Been developing this AI agent framework for 1 year now. It's very similar to n8n, but exclusively for open-source LLMs. It also just recently got MCP support.

The project is https://kdeps.com

I'm the developer of kdeps.com, and I really like Google Cloud Run, been using it since beta version. Kdeps outputs Dockerized full-stack AI agent apps that runs open-source LLMs locally, and my project works so well with GCR.

ATZ^M

AT&F^M

ATDT 12345678

I remember around 96-97, I have a broken HDD and no money to buy a new one, I don't have any windowing interface, and Knoppix wasn't released yet.

And for many months, I boot with a floppy with a Qmodem to dial into a BBS. I also remember running Quake on a CD-ROM. Later on, I get into freelance programming, then was able to afford a new PC.

I am nowhere near as big or as popular as Pydantic, but this is my solution - https://kdeps.com/getting-started/resources/python.html

I just came across this and shared it without much thought. I realize the title is controversial, and I don’t endorse offensive language. Just an interesting find in John Lennon’s history.

Currently, Docker does not support Metal GPUs.

When running LLMs on Docker with an Apple M3 or M4 chip, they will operate in CPU mode regardless of the chip's class, as Docker only supports Nvidia and Radeon GPUs.

If you're developing LLMs on Docker, consider getting a Framework laptop with an Nvidia or Radeon GPU instead.

Source: I develop an AI agent framework that runs LLMs inside Docker on an M3 Max (https://kdeps.com).

If you are interested, I also made an AI assisted OCR API - https://github.com/kdeps/examples

It combines Tesseract (for images) and Poppler-utils (PDF). A local open-source LLMs will extract document segments intelligently.

It can also be extended to use one or multiple Vision LLM models easily.

And finally, it outputs the entire AI agent API into a Dockerized container.

Gitops orchestration tool to create manageable and predictable shell scripts in YAML. It uses shortest-path first graph to calculate the run-order based on its dependencies - https://github.com/jjuliano/runner

I made a graph-based orchestrator - https://github.com/jjuliano/runner - It uses declarative YAML, and preflight, postflight and skip conditions. I think it can also be a full-fledge build system.