Arash

Trying to figure out how to bind this

[Arash @rshthr]

Here's the link to the extension on the Chrome web store:

https://t.co/kMOYLRB5ok

[Arash @rshthr]

When moving from Firefox to @brave I had one problem: circular tab switching, so I made an extension for it.
Customizing software is now easier than ever. https://t.co/8pUJfBP7iy

[Arash @rshthr]

@paulg I keep thinking about the idea of making readable, compilable DSLs that can be fed to the LLM

[Arash @rshthr]

@coolcoder56 What live coding? Real coding now mostly happens with AI

[Arash @rshthr]

This part of the "llama.cpp Manifesto" caught my attention:
> Hacking small tools and examples is a great way to drive innovation. We should not get lost into software engineering problems. Especially at the beginning, the goal is to prototype and not waste time in polishing products

[Arash @rshthr]

https://t.co/EwJiOuXpqM

[Arash @rshthr]

Great idea to replace the phone usage in the morning.
I've made my own automation to get a summary of the blogs I follow in the morning. More on my blog.

[Ryan Doyle @doooyle]

surprised more people aren't doing something like this

Codex now creates a "newspaper" for me every morning

Unread messages, calendar, surf report, news

Anything I can do to stay off my phone until later in the day is a priority

[Arash @rshthr]

Hey Ryan,
Thanks for the inspiration. Now I've created a daily automation to get a summary of all the blogs I follow + my daily tasks and emails in print.
Every morning I wake up with the sound of the printer and this bulltine is the first thing I pick up. No more phones in the morning.

[Arash @rshthr]

I'm so excited about this new era, but let's also acknowledge what we lost along the way.

[Kent Beck 🌻 @KentBeck]

Programming lost its flow state. The agent world feels more like air traffic control.

What I miss most: feeling oriented, a sense of mastery. That loss is emotional, and when software gets fiddly, practical too.

More on Still Burning: https://t.co/hB2v13obl0

[Georgi Gerganov @ggerganov]

llama.cpp at 100k stars

now that 90% of the code worldwide is being written by AI agents, I predict that within 3-6 months, 90% of all AI agents will be running locally with llama.cpp 😄

Jokes aside, I am going to use this small milestone as an opportunity to reflect a bit on the project and the state of AI from the perspective of local applications. There is a lot to say and discuss and yet it feels less and less important to try to make a point. Opinions about viability of local LLMs are strongly polarized, details are overlooked, the scientific approach is lacking. Arguments are predominantly based on vibes and hype waves.

One thing is clear though - local LLMs are used more and more. I expect this trend to continue and likely 2026 will end up being one of the most important years for the local AI movement.

I admit that I didn't expect the agentic era to come so quickly to the local LLM space. One year ago, the available models were too computationally expensive for doing long-context tasks. There wasn't an obvious path towards meaningful agentic applications. The memory and compute requirements were huge. Last summer, with the release of gpt-oss, things started to change. It was the first time we saw a glimpse of tool calling that actually works well within the resource constraints of our daily devices. Later in the year, even better models were released and by now, useful local agentic workflows are a reality.

Comparing local vs hosted capabilities at a given moment of time is pointless. To try put things into perspective:

- We don't need frontier intelligence to automate searches and sending emails
- We don't need trillion parameter models to be able to summarize articles or technical documents
- We don't need massive GPU data centers to control our home appliances or turn the lights off in the garage

I believe that there is a certain level of intelligence we as humans can comprehend and meaningfully utilize to improve our working process. Beyond that level, access to more intelligence becomes unnecessary at best and counterproductive at worst. I also believe that that level of useful artificial intelligence is completely within reach locally and it has always been just a matter of implementing the right software stack to bring it to the end user.

With llama.cpp, I am confident that we continue to be on the right track of building that software stack!

The llama.cpp project is going stronger than ever. With more than 1500 contributors, the project keeps growing steadily.

From technical point of view, I think that llama.cpp + ggml is the only solution that actually makes sense. That is, the software stack must run efficiently on every possible device, hardware and operating system. The technology is too important to be vendor-locked. It has to be developed in the open, by the community, together with the independent hardware vendors. This is the only right way to build something that will truly make a difference in the long run.

I won't try to convince you about what is currently and will be possible with local AI. We will just continue to build as usual. I am confident that after the smoke clears and we look objectively at what we have built together, the benefits will be obvious to everyone.

Big shoutout to all llama.cpp maintainers. I feel extremely lucky to be able to work together with so many talented contributors. Every day I learn something new and I feel there is so much more cool stuff that we are going to build. Also, I am really thankful that the project continues to have reliable partners to support it!

Cheers!

[Arash @rshthr]

@ibocodes I'm a full believer in their products. Only place you find some sanity!

[Ryan Dahl @rough__sea]

I really don't want to be vegan.

Because actually I have no problem with killing animals for food - it's just the way of the world.

I don't even really mind torturing animals for food - as long as they're low cognition (fish, insects, etc)

However - I really don't want to participate in the active (often life long) torture of high cognition animals like pigs.

Chickens are pretty dumb, but I'm not down with stuffing them into small cages their whole lives to peck at each other.

Not ok with dairy cow-calf separation.

And the more you look into it, the more you realize that humane sources of meat, dairy, and eggs are VERY hard to come by. Buying the more expensive brand at the grocery store does not imply torture free.

If you're eating bacon, an egg, cheese from a random restaurant - you are participating and enabling animal torture.

These labels "vegan", "vegetarian", "pescatarian" don't work for me. A vegetarian who eats dairy and eggs still participates in torture.

I would lustfully eat a steak that had a good life, or an egg from a non-factory farm.

For all the daily political bullshit that happens - the torture of billions of animals is so rarely discussed.

[Arash @rshthr]

Today I accidentally bumped into @EskilSteenberg while biking home. We ended up having the most amazing, refreshing conversation about finding problems, scalable solutions, UB in C and Project Hail Mary! What a great person. Can't wait for his presentation at @BetterSoftwareC

[Arash @rshthr]

I built simple Git-based CMS for Hugo static site generators.
No backend, no database, no configs. Just login with Github, select your repo and start editing.
If you use Hugo for blogging, feel free to check it out at https://t.co/nOyT39Fyyj

[Arash @rshthr]

@jessitron Because they don't have the desire. I think that's the main difference.

[Arash @rshthr]

There will come a day that we send an AI to a parliament.

[Arash @rshthr]

@lauriewired Wait for the copyright infringement letter from Postgres

[Arash @rshthr]

@kapilansh_twt Digital Equipments Corporation

[Arash @rshthr]

@fresheyeball Jokes on you. I'm using Emacs

[Arash @rshthr]

@TrisH0x2A PR reviews