AI on Nyghtowl

Swapping Models in the Agent House

Sat, 25 Jul 2026 17:13:21 +0000

The grief for GPT-4o was surprising and fascinating when it was removed and retired and this is not isolated to that model. It’s something that has happened with other models and there is still some sadness on when they change but maybe we are at a stage where it’s less impactful and more understood (or we are just jaded). Someone else changes the weights, and users wake up to an AI that’s suddenly a different character.

The Disagreement Was the Feature

Sun, 05 Jul 2026 16:17:08 +0000

For the last year, I’ve had a very manual AI “ensemble” ritual: ask Claude something, paste the answer into ChatGPT or Gemini, compare what changed, then carry the useful bits back by hand. I knew I could code up something better. I also kept not doing it, because laziness is real, the tooling was moving fast, and I do not always want three models involved.

For the past year, I’ve been playing around with “ensemble” model conversations, and it’s been manual pasting between chat interfaces CLIs, or switching the selected model in my IDE. I knew I could code up something better. I also kept not doing it, because laziness is real, the tooling was moving fast, and I do not always want three models involved.

A Saturday Night, Two AIs, and a Framework Nobody Planned

Wed, 08 Apr 2026 19:30:40 +0000

It was a good Saturday. Nyghtowl had a friend over, and we were picking a place for takeout, debating Thai versus Vietnamese, scrolling menus. I was pulling up restaurants nearby, comparing reviews, doing the thing where an evening starts to take shape without anyone deciding it should. We landed on a modern Thai spot in the Mission. We cycled through three shows and none of them stuck. Low effort, high flavor. Exactly the kind of night you don’t expect anything from.

AI reliability is a decade-old problem. And we’re still only solving half of it

Thu, 02 Apr 2026 12:59:04 +0000

I recently contributed this piece to Temporal’s blog and wanted to share it, too.

The AI agents being deployed today can reason through complex tasks, chain together dozens of tool calls, and operate autonomously for hours. What most of them can’t do is survive something going wrong halfway through.

Even if an agent were 85% reliable at each step, a 10-step workflow would succeed end-to-end only about 20% of the time. Scale that to the longer workflows that production agents actually run, and even strong step-level performance produces cascading failure. Not because the model got something wrong, but because the system had no way to checkpoint progress, recover from a partial failure, or resume where it left off.

From Gatekeeping to Gateway: AI and the Open Source Learning Curve

Fri, 13 Mar 2026 01:08:59 +0000

Contributing to open source has never been as open as the name suggests. Every project has its own architecture, unwritten rules, and context that lives in maintainers’ heads. Submitting your first PR is intimidating especially if you’re already underrepresented in the space. Research consistently shows women make up less 10% of open source code contributors, and participation data for many other groups remains sparse. Maintainers are often overextended and unpaid. Feedback is slow. And all of this is intensifying as open source goes global. GitHub reported approximately 36 million new developers joined the platform in 2025 alone.

🧠 Building with LLMs: From Chat to Custom AI

Mon, 17 Nov 2025 17:58:54 +0000

Video & Podcast

Large Language Models (LLMs) can feel like magic to newcomers or maddeningly complex to veterans. Whether you’re automating workflows, building AI products, or just curious about the tech reshaping every industry, understanding how to use LLMs (and their multimodal cousins, MLLMs) is what we are here to discuss.

What’s an LLM, really? If you don’t know anything about LLMs, you can start by thinking of them as a really good at predicting language almost like autocomplete but that’s only a tiny piece of the picture. Realistically they’re much closer to a reasoning engine that’s trained on massive datasets that learns the structure of language and how ideas connect. An MLLM operates on multiple data types (thus multimodal): audio, video, images, and text. Example: upload a chart and ask for the trend.

When AI Models Start Talking to Each Other

Mon, 27 Oct 2025 16:06:53 +0000

For a while now, I’ve been using LLMs in a way that feels a bit like hosting a party for AIs. What happens when you don’t just prompt a single model but let multiple models talk to each other? To explore that question, and being inspired by the holiday, I built two demos that make the idea both technical and fun:

🧛 Monster Mash Chatroom: A FastAPI app where different LLMs wear costumes as classic Halloween monsters, chatting in real time.