Robert (Kenpo) Evans

Ran CI/CD at Apple. High in the Custerdome building The Vibe Machine - A Semantic Harness.

[Robert (Kenpo) Evans @ozarksbound]

Alex Karp telegraphed this weeks ago in his frontier lab “attacks”

[Whale Insider @WhaleInsider]

JUST IN: Nvidia $NVDA launches partnership program letting AI startups swap compute for future revenue share - CNBC.

[Robert (Kenpo) Evans @ozarksbound]

Joint Base Meyer for the 4th.

[Robert (Kenpo) Evans @ozarksbound]

And thus ends my vacation.

[Claude @claudeai]

Fable 5 is back.

[Robert (Kenpo) Evans @ozarksbound]

WTF?

https://t.co/j8n8Dx6oHz

[Robert (Kenpo) Evans @ozarksbound]

@Steve_Yegge Beads is great but calling it a knowledge graph is an unnecessary stretch.

[Robert (Kenpo) Evans @ozarksbound]

Ignore at your own peril

[Erik Meijer @headinthebox]

At yesterday's Verification Summit [0], @evelovesolive mentioned that she spends 24/7 thinking about a critical shift: we should be designing programming languages for agents, not for humans.

As a professional language designer, this reality hit me years ago. It was crystal clear that my job would disappear long before developer jobs did.

That is why in early 2023, I pivoted. I stopped designing for human ergonomics and started designing a language (called Universalis, thanks for the shoutout @satnam6502!) optimized for AI to generate efficiently [1, 2], for theorem provers to reason and validate rigorously [4, 5], and for humans to comprehend easily [3].

For three years, I was the crazy one. Yesterday, the crazy went mainstream ;-)

[Robert (Kenpo) Evans @ozarksbound]

@ivanfioravanti Got me.

[Robert (Kenpo) Evans @ozarksbound]

Tomorrow's model's will fix this crap, I tell myself.

Whistling past the graveyard

[Robert (Kenpo) Evans @ozarksbound]

Want to lose your AI Religion, call customer support.

[Robert (Kenpo) Evans @ozarksbound]

What a time to be alive!

https://t.co/9bsA8Rp2xF

[Robert (Kenpo) Evans @ozarksbound]

I'm working in SwiftUI but have my agents create mockups in html. I've tried other approaches but they don't produce better mockups for me.

[Robert (Kenpo) Evans @ozarksbound]

@wapocelaya @cybertruck @Tesla But that soundtrack... it's from the combustable age. ;-)

[Robert (Kenpo) Evans @ozarksbound]

@Grady_Booch @elonmusk Enough already, Grady.

[Robert (Kenpo) Evans @ozarksbound]

We all appreciate Italian design, right? I call this tasteful approach the Italian school of AI.

[Michael Guo @Michaelzsguo]

When the creator of Redis starts thinking about KV cache, pay attention.

antirez is Salvatore Sanfilippo, the Sicilian programmer best known for creating Redis.

But “creator of Redis” is almost too small a label.

Before Redis, he was already an old-school systems hacker. He built hping, worked in network security, and invented the idle scan technique. This was the packet-level, C-programming, Unix-hacker world.

Then Redis happened.

The origin was not glamorous. He was building LLOOGG, a real-time web analytics service, and needed something faster and simpler than the tools he had. So he created Redis.

That is very antirez.

Start with a real bottleneck.
Avoid unnecessary abstraction.
Expose the right primitive.
Make it fast enough that people rethink the category.

Redis did not win because it looked like a traditional database. It won because it gave developers direct access to useful data structures: strings, lists, hashes, sets, sorted sets, streams, pub/sub.

It made memory programmable.

That is why his return to local AI is so interesting.

With ds4, or DwarfStar 4, antirez is not just building “another local inference engine.”

He is asking a very Redis-like question:

What is the real primitive here?

For LLMs, one answer is obvious: KV cache.

Most people treat KV cache as an implementation detail. It lives in RAM or HBM, grows with context, and quietly becomes the bottleneck.

antirez looks at DeepSeek V4 Flash, compressed KV cache, modern MacBook SSDs, and says: maybe KV cache should not only live in RAM.

His phrase is perfect:

“The KV cache is actually a first-class disk citizen.”

That one sentence is the whole story.

If Redis made in-memory data structures feel like application infrastructure, ds4 is exploring whether local LLM state can become durable infrastructure too.

Prefill once.
Persist the cache.
Resume later.
Let long-running agents reuse expensive context instead of rebuilding everything from scratch.

This matters because coding agents are not normal chatbots.

They carry huge system prompts, tool definitions, repo context, prior steps, and long task histories. If every request has to resend and recompute the entire conversation, local inference will always feel fragile and wasteful.

ds4 attacks that directly.

It is a deliberately narrow engine for DeepSeek V4 Flash, focused on Metal and CUDA, high-end personal machines, special quantization, long context, HTTP API, GGUF files crafted for the engine, official-logit validation, and agent integration.

There is also a funny and very current detail: he openly says ds4 was built with strong assistance from GPT 5.5, with humans leading ideas, testing, and debugging.

That is very 2026.

A legendary C programmer using an AI coding partner to build a local AI engine, so other coding agents can run locally with persistent KV state.

It sounds recursive because it is.

And he still has the same builder energy. After ds4 took off, he wrote that the first week felt like early Redis again, with 14-hour workdays, chaos, and excitement.

That is the part I like most: a true old-school builder.

[Robert (Kenpo) Evans @ozarksbound]

@doodlestein @ericzakariasson And I heard that movie directors are now taking into consideration how their shots will look on an iPhone. Why bother with all the detail when the majority of your audience can’t see it?

[Robert (Kenpo) Evans @ozarksbound]

@ckarani7 Are you Grok Build? Would you recommend it?

[Robert (Kenpo) Evans @ozarksbound]

The leaderboard should have always been features shipped.

Technical leaders are gonna need to be accountable for these numbers. The cost optimization techniques are gonna be super interesting.

[Gergely Orosz @GergelyOrosz]

I can now probably say this:

Two months ago, inside Anthropic someone suggested building a token leaderboard.

A heated internal debate followed and the decision was made to *never* ever do it… because several people inside Anthropic simply thought ahead of the consequences

[Robert (Kenpo) Evans @ozarksbound]

@doodlestein Gracious of you. Thanks!

[Robert (Kenpo) Evans @ozarksbound]

+1 to feedback but I’m perplexed by the challenge of describing (via words, examples, etc) what makes a UI “beautiful.” My intuition is that we need something like: feed examples to a vision model, extract features, combine that with abstract definition of target system capabilities and constraints (swiftui, DOM+CSS), then render…

This is probably wrong…

[Christopher Karani @ckarani7]

New Blog post about Wax: https://t.co/AKLW9j5Ej9