Preslav Rachev

Indeed, context size is the killer. We have 64GB on that GPU machine, and that's barely enough for anything bigger than 100K tokens. And I think, context window RAM needs grow somewhat exponentially, TBH

Same! Hehehe, not at all - my approach to licensing is, anyone can use whatever they want, as long as they like the products enough that they want to chip in their future development.

P.S. will send you a DM sometime later today with more details how to join the v2.0 beta.

We tried it with qwen-coder-3 running in a big beefy machine, but the agent just basically ran around for a while just wasting GPU cycles.

Think of it like someone who moved from engineering to engineering management. You still have your final say and are hands-on, just not dealing with the nitty gritty.

Funny - the very first Go framework I wrote that later became the foundation for Murmel, was called Burrow :)

We largely rewrote everything, though, now that we’re close to releasing v2.0 of Murmel

I prefer buying songs from ITunes (yes, it’s still very much alive) than using any subscription service, for the same reason I bought a bulky digital camera in the era of computational photography. I like when things are intentional, and not just something that runs in the background of my life.

I am sorry, Rust, but you lost me at:

|a: usize| async move { Ok::<_, BoxDynError>((0..a).collect::<Vec<_>>()) }

#rust #programming

Society? What does that even mean? I am generalizing, of course, there are good examples out there, but we have to wait a few more years for this syndrome to perish, so we can step up on some more solid civic principles.

Bulgaria has achieved the Western dream it's been craving for so long. Bulgarians are now richer than they have ever been, but also, completely disintegrated, and lost for meaning beyond buying their next luxury SUV, or traveling somewhere their parents weren't able to. 1/2

And that's awesome. I love native Mac apps, and I am willing to pay premium for the closer-to-metal experience. But you see, even Apple is giving up on design principles. And if they don't enforce strict design uniformity from the top, the end user will seriously question if the premium is worth it.

Commentary on Brandolini’s Law Brandolini defined the following law: The amount of energy needed to refute bullshit is an order of magnitude bigger than that needed to produce it. It normally applies to arguments and misinformat…

“The authenticity of content will become more important than its quality.”

veselin.blog/2026/03/05/c...

Claude is an Electron App because we’ve lost native Article argues that Claude is not an Electron app not because LLMs can’t do it, but because there are no advantages left for native

I highly recommend you to read this recent article by @tonsky.me: tonsky.me/blog/fall-of...

In short, going all native is a lost cause, unless OS vendors themselves start once again getting native seriously. It’s been disintegrating for decades.

I’m considering getting one of the smaller reMarkable Paper Pro Move devices to try it out. I was a big fan of the RM2, and to this day feel sorry I sold it in a rush. People have had mixed feelings about the Move, but were equally wrong about the SuperNote (which I found a complete disappointment)

Large language models are modern day’s Schrödinger’s Cat. They see non-deterministic, but down to the core, they are very, very deterministic. Anything based on pseudo-randomness is deterministic by nature.

but I’m curious if they really want to task an LLM to pilot a drone (there are far better models for that) or for something else. Or, is it simply a media ploy to scare the nation.

When one says the US is going to use Anthropic’s or OpenAI’s LLMs for military purposes, what do they really mean? I’ve been using these tools for a few years now, and certain use cases pop to mind ... 1/2

1995: From Batman Forever’s cinematic design to HTML tables 1995 begins with web designers creating cinematic experiences using images and browser tricks, and ends with the arrival of table support in Netscape Navigator — giving true control over layout.

“If 1994 was when the Web became a publishing medium, then 1995 was when the Web truly marked itself as a unique expressive medium. The Web became a place — a destination — rather than a mere repository for documents.” — @ricmac.cybercultural.com

cybercultural.com/p/1995-web-d...

Writing about Agentic Engineering Patterns I’ve started a new project to collect and document Agentic Engineering Patterns—coding practices and patterns to help get the best results out of this new era of coding agent development …

@simonwillison.net is the first I've heard use the term "agentic engineering", which feels like a much better description of how I use tools like Claude Code (as opposed to "vibe coding", which implies no human architecting the result). Great stuff in this post:

simonwillison.net/2026/Feb/23/...

spec: generic methods for Go · Issue #77273 · golang/go Proposal: Generic Methods for Go A change of view. Background For clarity, in the following we use the term concrete method (or just method when the context is clear) to describe a non-interface me...

🚀 "spec: generic methods for Go" has been accepted!

You will soon (1.27?) be able to declare (on concrete types only) methods that introduce type parameters, i.e. type parameters other than the ones (if any) that come from the method's receiver.

github.com/golang/go/is...

#golang

It works, but it requires a lot of time and patience.

Don’t Fight the Weights When your context goes against a model’s training, you struggle to get the output you need. Learn to recognize when you’re fighting the weights so you can do something different.

It helps to think of LLMs as bell curve statistical optimizers. Most code they've been trained on, would likely simply concatenate strings using plain operators. And, this is what they pick most of the time.

Teaching them new tricks is called "fighting the weights." www.dbreunig.com/2025/11/11/d...

I know the feeling. You subscribe to 100 blogs, where you only really read 1%. This is one area we've been trying to improve with the release of @feedle.world - instead of having to subscribe to hundreds of RSS feeds, we create ones per topic, sourcing posts from thousands of blogs and podcasts.

Plenty of businesses failed before AI, and plenty will fail with it. The tooling may have improved, but reality is as harsh as ever. A bad idea with AI is still a bad idea, just shipped faster.

Но пък доброто е, че всеки път се получава нещо ново, и по-добро от предното.

Twenty years is proper perspective. I've landed in a similar place - the agent needs to be on a tight leash with clear boundaries, not given free rein. The moment you stop reviewing its output is the moment it quietly introduces chaos.

Twenty years of context is exactly what makes the difference. The bit most people miss is that "remaining in control" also means owning the context the agent works with - if your codebase knowledge lives on someone else's server, you've already ceded control before the first prompt.

What you see from most folks leaving Claude Code to work alone, is some random mid web app that looks like every other. Remarkable nonetheless, but also, very mid, unless you really step in the product owner shoes, and do a ton of AI hand-holding.

I’ve been programming for over 20 years now, the last three of which, using AI tooling almost exclusively. Here is the bottom line:

It’s not.

You can achieve great results with agentic tooling, but only if you consider the agent your junior programmer assistant.

You must remain in control.

Welcome to the #golang club!

FTR, if you write code that you'd like your future self to understand, yes, more lines do actually make it easier. Go was not meant for writing ergonomics, but for that of reading (especially by newcomers).

Plus, AI agents have finally solved the writing part for us.