iamwil's Avatar

iamwil

@interjectedfuture.com

Tech Zine Issue 1: LLM System Eval https://forestfriends.tech Local-first/Reactive Programming ⁙ LLM system evals ⁙ Startup lessons ⁙ Game design quips. Longform: https://interjectedfuture.com Podcast: https://www.youtube.com/@techniumpod

1,882
Followers
334
Following
1,627
Posts
17.04.2023
Joined
Posts Following

Latest posts by iamwil @interjectedfuture.com

Screenshot of several images from my new blog post

Screenshot of several images from my new blog post

Blog post: I've been working on a guide to SDF font rendering, and I kept getting stuck. The blog post is about the things that didn't work www.redblobgames.com/blog/2026-02...

05.03.2026 04:13 👍 35 🔁 7 💬 3 📌 0
Post image

File this under more of "The future is weird, for anyone paying attention."

x.com/dioscuri/st...

04.03.2026 20:00 👍 1 🔁 0 💬 1 📌 0

I wish he called it a Familiar or a Summon.

There's a direct line from Claude Shannon to Lobster Appendages. Hope etymologists are taking note.

x.com/karpathy/st...

04.03.2026 16:00 👍 0 🔁 0 💬 0 📌 0

By forcing me to log in, Perplexity just...makes me stop using it.

04.03.2026 07:40 👍 1 🔁 0 💬 1 📌 0

Is writing outsourcing our thinking? Socrates seemed to think so.

02.03.2026 03:54 👍 1 🔁 0 💬 0 📌 0

Is there any talk about clawing it back with upcoming classes of Congress? Or they've just kinda let it go, given how often we're just in low-key wars?

28.02.2026 20:31 👍 0 🔁 0 💬 1 📌 0

Honest question: I thought only congress had the power to declare war. I know that’s been weakened in recent decades. Have they given up on it altogether?

28.02.2026 19:46 👍 0 🔁 0 💬 1 📌 0

Ah. I assume they have a base implementation that adheres to the protocol, but with these forward looking variants on top, which other peers ignore if they don't understand it, but it doesn't break the protocol?

28.02.2026 00:46 👍 0 🔁 0 💬 1 📌 0

I don't have a lot of context, so bear with my dumb question: are buckets experimental, or are they something that's landed on AtProto?

28.02.2026 00:09 👍 0 🔁 0 💬 1 📌 0
Anatomy of an LLM connection string

llm://app-name:password@api.openai.com/gpt-5.2?temp=0.7&max_tokens=1500

The scheme is llm://. The host is the provider’s API base URL. The path is the model name. And query parameters handle all the runtime options that usually clutter your code.

Anatomy of an LLM connection string llm://app-name:password@api.openai.com/gpt-5.2?temp=0.7&max_tokens=1500 The scheme is llm://. The host is the provider’s API base URL. The path is the model name. And query parameters handle all the runtime options that usually clutter your code.

Being a bit of a URL nerd, I love this idea

danlevy.net/llm-connecti...

27.02.2026 07:44 👍 23 🔁 1 💬 1 📌 0

Is there an OpenClaw for managing your Kubernetes cluster? Or is the OpenClaw of Kubernetes management just OpenClaw?

27.02.2026 19:30 👍 0 🔁 0 💬 0 📌 0
Preview
The Pentagon is making a mistake by threatening Anthropic Anthropic faces a Friday deadline to allow domestic surveillance and automated killer robots.

www.understandingai.org/p/the-penta...

27.02.2026 19:00 👍 1 🔁 0 💬 0 📌 0
Post image

The future is so weird. It's hard to express to people not paying attention as to how weird it really is.

27.02.2026 19:00 👍 20 🔁 6 💬 1 📌 0

Selling to people though, I think will still have humans in the loop for a long while.

27.02.2026 16:56 👍 1 🔁 0 💬 0 📌 0
Post image

A follow on consequence of this is that people will try to figure out how to do sales to agents. And subsequently, how to get agents to sell to agents.

Agent-led sales.
x.com/snowmaker/s...

27.02.2026 16:56 👍 1 🔁 0 💬 1 📌 1

So if big tech uses industrial processes like agentic engineering to code, and most of agentic engineering is making architectural decisions in specs and Q&A; I would think that interviews would now focus mostly on systems design questions.

27.02.2026 16:00 👍 1 🔁 0 💬 0 📌 0

One of the big step change difference between Opus 4.5 and 4.6 for me was....that it could one-shot kubernetes configuration of ingress for ActivityPub on my blog.

27.02.2026 03:48 👍 2 🔁 0 💬 0 📌 0

Sometimes, the scar tissue of doing something sucky (like dev ops) makes me procrastinate on doing it, when in reality, it's much quicker with agents now.

27.02.2026 01:43 👍 0 🔁 0 💬 0 📌 0

I bet you 150k token context window looks like a million token context window to those that write APL.

26.02.2026 17:00 👍 2 🔁 0 💬 1 📌 0

With so many more non-traditional coders being turned onto coding via agents, this is one of those rare demographic and platform shifts.

So if any APL/Datalog/Haskell fans want to indoctrinate new programmers, now is the time. Notation as a Tool for Thought as a way to prompt.

26.02.2026 17:00 👍 5 🔁 1 💬 1 📌 0

If programming is theory building, then lots of people aren't building any theory on the technical shape of the problem, because the tools are inadequate during review. Not only are we bottlenecked there, but we're also becoming detached.

26.02.2026 16:00 👍 3 🔁 0 💬 0 📌 0

I have a mildly cold take

bsky.app/profile/inte...

26.02.2026 15:38 👍 0 🔁 0 💬 0 📌 0
Preview
GitHub - pfrazee/infocivics: Information Civics paper Information Civics paper. Contribute to pfrazee/infocivics development by creating an account on GitHub.

Just learned a new term "Info Civics". System evals for certain public services should be public, like we have with the court of law.

github.com/pfrazee/inf...

26.02.2026 02:00 👍 0 🔁 0 💬 0 📌 0
Preview
Practical Decentralization The point of decentralization is to guarantee the rights of individuals and communities on the Internet. Pulling that off is a balancing act between practicality and ideology.

I've been watching AtProto from afar. So far, I've liked what I see, and when it comes to decentralization, I really like how pragmatism is in the list of considerations.

www.pfrazee.com/blog/practi...

26.02.2026 02:00 👍 0 🔁 0 💬 1 📌 0

I just wrote about this. Haha.

bsky.app/profile/inte...

25.02.2026 21:05 👍 1 🔁 0 💬 1 📌 0

It'll provide a long tail of software never seen before, which will spring forth new industries. It'll have long-reaching second-order effects like the aforementioned drive-thrus and highways, now that intelligence is on tap.

25.02.2026 20:26 👍 1 🔁 0 💬 0 📌 0

For everything else one has midwit tastes and needs for, we'll probably lean on industrially produced software using agentic software processes. It'll democratize access to using computers, not just as a consumer, but as a producer. Or even just to let us focus higher on the meta

25.02.2026 20:26 👍 1 🔁 0 💬 1 📌 0

There will still be artisanal coders in the future, either for luxury or status signaling products. And they will provide an experience far better beyond what industrial software could provide, *if* you're sensitive to it--an otaku for that sort of thing.

25.02.2026 20:26 👍 1 🔁 0 💬 1 📌 0

In the long term, new ways of building will be around the process of managing the agent build process and understanding the mathematical nature of composition, in the same way current industrial manufacturing innovation is around process and material science.

25.02.2026 20:26 👍 1 🔁 0 💬 1 📌 0

So I think coding by hand is important in the near term for finding new forms and ways of building, since LLMs currently have a hard time drawing the right system boundaries and abstracting beyond what's shown in the current training data.

25.02.2026 20:26 👍 1 🔁 0 💬 1 📌 0