David Foliti

Building useful things

[David Foliti @marlenesco]

🎨 Tintary turns a single color into a complete, production-ready color system.

Generate 50–950 scales, semantic tokens, light/dark themes, contrast checks and exports for CSS, Tailwind, Material UI, Bootstrap and Tokens Studio.

Free, no signup:
https://t.co/IYN2RosePy

[David Foliti @marlenesco]

@Franco942933 @ABianconer1 @pap1pap Effettivamente rispetto alla "quesrtione Recoba" si tratta di un fatto gravissimo, da Narnia è tutto

[David Foliti @marlenesco]

@techartist_ I made a similar thing, it is on github: https://t.co/j6FQq2mKMr.

[Benonwine @benonwine]

I think I speak for a lot of people when I say this.

For years, Sunday nights meant Top Gear. We’d sit down at 8pm and watch Jeremy Clarkson, Richard Hammond and James May do what they did best.

Now, through Clarkson’s Farm, Jeremy has introduced a whole new generation to the realities of British farming and earned the respect of millions all over again.

He’s made us laugh, he’s frustrated us, and he’s entertained us for decades.

Get well soon, Jezza.

The country is rooting for you. ❤️🇬🇧🙏

[Matteo Collina @matteocollina]

A default set from May 2015 was just changed for the first time.

One number. One constant. And it was quietly costing Node.js up to 26% of its throughput on the workloads you run every day: file reads, HTTP parsing, and stream chunking.

Nobody broke it. The world just moved on.

[antirez @antirez]

Btw I believe we have a mostly wrong framing of what could be done in Europe. Italy's Leonardo supercomputer datacenter alone plus Swiss National Supercomputing Centre has more than enough compute to train a very large LLM. It's not something impossible, also there is not magic recipe: it's just scaling, every smart team with the GPUs is doing it. People that fatally believe it is not something within reach are wrong.

[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.

[David Foliti @marlenesco]

@antirez @lastknight @NousResearch Conoscevo già la risposta Salvatore, se hai già un gruppo di persone per l'hardware fammi sapere, @lastknight vieni, ti aspettiamo

[David Foliti @marlenesco]

@0zen_ Dovevi chiamare la gendarmeria, Gratteri e i reparti speciali, Sergione per assicurarti che non lo graziasse e farlo rinchiudere a Rebibbia

[Corben Leo @hacker_]

Whoops....

https://t.co/z2dRXueHpo

[David Foliti @marlenesco]

@Fidelio1971 @AlessioPiana130 Rossi gibernau allora cosa era?

[David Foliti @marlenesco]

@HenRRic_Swe Lucky guy, enjoy that dope

[Jonathan Fine @jonathanbfine]

remember when we fired Elon Musk and he just ignored it

[Kim Dotcom @KimDotcom]

🤣

[Matteo G.P. Flora @lastknight]

https://t.co/dd1o7VxkrA

[David Foliti @marlenesco]

@Luca27125188 @whatsgoingahn @claudioborghi Eni estrae anche petrolio in Venezuela, basta una rapida ricerca

[Lukas Ziegler @lukas_m_ziegler]

Omni-directional machines in action! 🎡

These robots made with the LEGO Group brick can move smoothly in any direction, and rotate in place.

That makes very precise motion control for both manual driving and autonomous behaviors.

This particular omni-directional vehicle system is a fan-made LEGO® MOC (My Own Creation), built entirely from LEGO bricks.

It includes custom omni-directional vehicles along with dedicated floor plates designed to support accurate motion.

That's a proper project for robotics people!

Let's build more in 2026.

Creator's page: https://t.co/wrbwrm7xCk

~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB