Sem 🏴️‍

Sem 🏴️‍

@ssinchenko.bsky.social

Big Data, Open Source, Privacy, Photography, Anarchism. View my blog: https://semyonsinchenko.github.io/ssinchenko/

486 followers677 following375 posts

Pinned

Sem 🏴️‍
@ssinchenko.bsky.social

This is an old post from 2023, but it think it still may be interesting for anyone, who is thinking about #cycling adventure in #Serbia or at #Balkan region in general. The story of my 700km trip along Danube river and a way back. #bikesky semyonsinchenko.github.io/ssinchenko/p...

semyonsinchenko.github.ioCycling Eastern SerbiaI would like to tell you about my bicycle trip through Eastern Serbia. This part of the world is beautiful, but there is a big problem with lack of information in English. So I will try to fill this g...

Sem 🏴️‍ reposted

Andrew Lamb
@andrewlamb1111.bsky.social

Great blog from Tim Saucer, an @apachedatafusion.bsky.social PMC member and core maintainer, about why agent dump PR actually hurts (along with some good suggestions on how to make the contributions actually helpful): timsaucer.com/2026/09/14/t...

timsaucer.comThat pure AI contribution is not contributing much - Tim SaucerIn my open source work on Apache DataFusion, I’ve seen this growing trend of people finding an open issue and having an AI agent author the complete solution with no real input from the author. We’ve ...

Sem 🏴️‍ reposted

Orhun Parmaksız
@orhun.dev

DOOM in the terminal! 👾 plurimus-doom — DOOM rendered with colored half-block characters ⚡ CPU and GPU modes, CRT shaders, edge effects, braille, ASCII & shading ramps 🦀 Written in Rust & powered by @ratatui.rs ⭐ GitHub: github.com/kenianbei/pl... #rustlang #ratatui #tui #doom #terminal

Sem 🏴️‍
@ssinchenko.bsky.social

AI changed for me the way how deep can I customize #Emacs. Lisp was a wall previously. But today all I need is to just tell LLM what I want. For example, GLM-5.3-flash just made for me a dashboard with manga reading progress as an org-file synced with "kitsu.app" API 🤩

Sem 🏴️‍ reposted

hailey
@hailey.at

you can now spend $15/mtok on sol, but somehow people will find a reason spending $50/mtok on fable is “the only way to complete their task” lol

Sem 🏴️‍ reposted

Luis Villa
@lu.is

For the first time since the ‘90s, my home box is a highly personalized, custom Linux desktop. Not because GNOME got worse, but because I had an idea *and* an LLM helped me actually *use* the freedom of FOSS to make the idea real. https://mastodon.social/@webchick/117067256281834909

mastodon.socialwebchick (@webchick@mastodon.social)“THEY STOLE OUR REVOLUTION, NOW WE’RE STEALING IT BACK.” @mjg59@nondeterministic.computer argues from the “origin story” of the free software movement that there are uses of LLMs as tools to solve th...
Sem 🏴️‍
@ssinchenko.bsky.social

To learn new things, maintain an emotional connection with code, and keep an ownership, I write code by hand. For personal projects ~70-80% by hand, for work projects ~15-20%. To not loose the "AI productivity boost," I made a SKILL that generates an "onboarding ticket" instead of code.

Sem 🏴️‍
@ssinchenko.bsky.social

Unlike Learning Mode or "Socratic modes," the focus here is on senior developers rather than junior developers, and the format is specifically "onboarding." The text includes a long section explaining why and how I did this, as well as how I use it. semyonsinchenko.github.io/ssinchenko/p...

semyonsinchenko.github.ioWhy I Still Write Code By Hand And How AI Is Helping MeA SKILL.md that makes my harness write an onboarding ticket instead of code: what to change, where, and why instead of copy-pasteable diffs. Like the Learning Mode, but written for a senior engineer w...

Sem 🏴️‍ reposted

Asa ⭔
@asa.engineer

Anthropic’s main purpose, in a posiwid sense, is to ensure that AGI runs on Huawei Ascend

Sung Kim@sungkim.bsky.social

What I don’t understand is this: people have repeatedly warned these supposed geniuses that restricting GPU sales to China would force China to absorb enormous short-term losses to build its own chip industry, while guaranteeing Chinese suppliers a CAPTIVE domestic market.

Sem 🏴️‍
@ssinchenko.bsky.social

I'm experimenting with out-of-core graph algorithms, such as finding all the connected components of a 2B-edge graph with a memory limit of 7 GB, etc. I'm starting to worry that it may just kill my disk — can it do that? Would it be better to use an AWS instance?

Sem 🏴️‍
@ssinchenko.bsky.social

That is cool to see more small focused models like this instead of boring tocenmaxxing!

mr. TIM@timkellogg.me

Cisco launches Anteres-350M, 1B & 3B local models for defensive cybersecurity, finding vulnerabilities blogs.cisco.com/ai/introduci...

Sem 🏴️‍ reposted

Asa ⭔
@asa.engineer

talk to your agent about the Jacobian Conjecture before it does too many web searches today

Sem 🏴️‍
@ssinchenko.bsky.social

I would say open-code-review from Alibaba is really cool. Paired with GLM-5.2 it catches things Claude cannot. Does not replace a human review but a very solid "starting point" especially for big pull-requests.

Sem 🏴️‍ reposted

Gergely Orosz
@gergely.pragmaticengineer.com

Let me know if this is just me: Noticed someone I know who is very "AI-pilled" and uses agents 24/7 to... start to talk IRL noticeably more like these LLMs write. Eg more heavily using adjectives like "geniune", frequently terms like "the shape of" and many more examples

View full thread
View full thread
Sem 🏴️‍
@ssinchenko.bsky.social

6/ But from a Bakuninist perspective, this was never mysterious. You do not get liberty by strengthening people whose politics are hierarchy, nationalism, police power, borders, and moral discipline.

View full thread
Sem 🏴️‍
@ssinchenko.bsky.social

4/ Right-wing populism did not weaken the state. It redirected resentment toward capturing the state, staffing it with different people, and using it for different forms of domination.

View full thread
Sem 🏴️‍
@ssinchenko.bsky.social

4/ So yes, this was absolutely vibecoded. But not in the “one prompt and a miracle” sense. It was built with OpenCode + OpenSpec, a lot of specs, tests, and repeated auditing. I would never have written this amount of weird personal Lisp infrastructure by hand.

Sem 🏴️‍
@ssinchenko.bsky.social

5/ I wrote a longer post about why “headless Emacs in Docker” ended up making sense here, and why I think LLMs are especially good for building narrow personal software instead of generic SaaS-shaped products: semyonsinchenko.github.io/ssinchenko/p...

semyonsinchenko.github.ioOrg Mode in the AI Era: Organize Your Life in Plain Text, Then Automate ItYes, I really ended up running headless Emacs in Docker Compose. Yes, it actually works. And yes, in this blog post I will explain why I think this setup makes much more sense than it sounds. I will s...
Sem 🏴️‍
@ssinchenko.bsky.social

2/ The idea is simple: mobile captures, TODO normalization, semi-automatic planning, RSS digests, and link capture into org-roam -- all through shared Org files over WebDAV, with Emacs as the backend/runtime.

Sem 🏴️‍
@ssinchenko.bsky.social

3/ The important part is that this is not an autonomous-agent setup. I assume LLMs always hallucinate, so all useful work happens inside strict contracts: validation, retries, DLQ, masked sensitive blocks, deterministic IDs, etc.