FeedCity

Using Codex CLI with gpt-oss:120b on an NVIDIA DGX Spark via Tailscale

Inspired by a YouTube comment I wrote up how I run OpenAI's Codex CLI coding agent against the gpt-oss:120b model running in Ollama on my NVIDIA DGX Spark via a Tailscale network.

It takes a little bit of work to configure but the result is I can now use Codex CLI on my laptop anywhere in the world against a self-hosted model.

I used it to build this space invaders clone.

Tags: ai, tailscale, til, generative-ai, local-llms, llms, nvidia, coding-agents, space-invaders, codex-cli

Game design is simple, actually

Game design legend Raph Koster (Ultima Online, Star Wars Galaxies and many more) provides a deeply informative and delightfully illustrated "twelve-step program for understanding game design."

You know it's going to be good when the first section starts by defining "fun".

Via Hacker News

Tags: game-design

This San Francisco museum, curated by a super-fan of the Beats, is a shrine to an incredibly influential cultural movement and a destination for folks keeping it alive today.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

You should write an agent

Thomas Ptacek on the Fly blog:

Agents are the most surprising programming experience I’ve had in my career. Not because I’m awed by the magnitude of their powers — I like them, but I don’t like-like them. It’s because of how easy it was to get one up on its legs, and how much I learned doing that.

I think he's right: hooking up a simple agentic loop that prompts an LLM and runs a tool for it any time it request one really is the new "hello world" of AI engineering.

Via Hacker News

Tags: thomas-ptacek, ai, fly, generative-ai, llms, ai-agents

Cole Escola (Oh, Mary!) is writing the screenplay for a Miss Piggy movie. Jennifer Lawrence & Emma Stone are producing. (Crossing my fingers for a Pigs in Space scene…)

💬 Join the discussion on kottke.org →

My trepidation extends to complex literature searches. I use LLMs as secondary librarians when I’m doing research. They reliably find primary sources (articles, papers, etc.) that I miss in my initial searches.

But these searches are dangerous. I distrust LLM librarians. There is so much data in the world: you can (in good faith!) find evidence to support almost any position or conclusion. ChatGPT is not a human, and, unlike teachers & librarians & scholars, ChatGPT does not have a consistent, legible worldview. In my experience, it readily agrees with any premise you hand it — and brings citations. It may have read every article that can be read, but it has no real opinion — so it is not a credible expert.

— Ben Stolovitz, How I use AI

Tags: ai-assisted-search, llms, ai, generative-ai

Kimi K2 Thinking Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July. They've now released the Thinking version, also a trillion parameters (MoE, 32B active) and also under their custom modified...

Speaking of Daft Punk, did you know they released some new music recently? Ok well, that’s not quiiiite true, but in late September, Epic launched the Daft Punk Experience in Fortnite and IMO it’s a) extremely cool, nd b) should be considered a part of the group’s official d...

At the start of the year, most people loosely following AI probably knew of 0 [Chinese] AI labs. Now, and towards wrapping up 2025, I’d say all of DeepSeek, Qwen, and Kimi are becoming household names. They all have seasons of their best releases and different strengths. The...

Space Type Generator is “a kinetic type generator” that’s a hell of a lot of fun to mess with.

💬 Join the discussion on kottke.org →

Pre-show: Casey dropped his 17 Pro 🗣️ The ATP Holiday Store is back! Order before 9 November! 🗣️ T568A & T568B Idea courtesy Adam Brandon Don’t Stop Believin’… An aside about podcast chapters and Apple’s recent news Follow-up: The current MacBook Pro design i...

Low Skilled Workers Are a Myth. “[Minimum wage jobs] are not low-skill. They simply require different skills, ones that not just anyone possesses.”

💬 Join the discussion on kottke.org →

In his most recent video, Evan Puschak takes a close look at Marlon Brando’s face and gestures in a scene from On the Waterfront to explain how Brando changed film forever.

And this is what makes Brando a genius: when his eyes betray his words. His voice says, “What do you really care?” But his eyes say, “Please care. Please show me that you care.”

Welp, time to watch On the Waterfront, I guess.

Tags: Evan Puschak · film school · Marlon Brando · movies · On the Waterfront · video

💬 Join the discussion on kottke.org →

OREO! OREOOREO! RE! ORE! OREORE! OREOREOREOREORE!

💬 Join the discussion on kottke.org →

I'm upgrading various plugins for compatibility with the new Datasette 1.0a20 alpha release and I decided to record a video of the process. This post accompanies that video with detailed additional notes. The datasette-checkbox plugin I picked a very simple plugin to ill...

Earth’s got a new moon! (Sort of.) “This asteroid is part of an elite cosmic club which acts like moons but aren’t.” If asteroid, why moon acting?

💬 Join the discussion on kottke.org →

Mark Gurman, reporting for Bloomberg, “Apple Nears Deal to Pay Google Roughly $1 Billion a Year for Siri AI Model” (gift link): Apple Inc. is planning to pay about $1 billion a year for an ultrapowerful [sic] 1.2 trillion parameter artificial intelligence model developed...

After completing another long solo walk, Craig Mod wrote about fullness: This is why I always say: Aim for fullness if you want happiness. If the creator itself came down from the sky at the end of a big walking and photographing and writing day and asked: Did ya do all ya...

Lego is considering making this fan-created Daft Punk set into an official set. YES PLEASE.

💬 Join the discussion on kottke.org →

Mark Gurman, reporting for Bloomberg, “Apple Nears Deal to Pay Google Roughly $1 Billion a Year for Siri AI Model” (gift link): Apple Inc. is planning to pay about $1 billion a year for an ultrapowerful [sic] 1.2 trillion parameter artificial intelligence model developed...