Konstantinos Zagoris (@kzagoris) header
Konstantinos Zagoris (@kzagoris) profile picture

Full-stack engineer & founder, Zagor Solutions. I build or rescue software. C#/.NET, TypeScript, PhD. Blog: https://xitter.gq/t.co/0PUN7J1BwZ · Father of 3.

Paphos, Cyprus
Joined October 2013
Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)Photo by Konstantinos Zagoris (@kzagoris)
If you've only seen the movie, check out the series the movie was cut from. It is absolutely amazing. One of the highest points of Greek TV from a Greek from Cyprus. Thank you my brother
The St Paisios show is absolutely phenomenal, but it can be hard to find online. The popular site people send is missing an episode. I've got every episode and re-encoded them without quality loss so the whole series is 10GB. Link to download: mega.nz/folder/5VcCzbyT#fhwc…
11
Hey, gamer lovers out there! Dungeon Master II (1995) now runs natively on macOS, Linux & Windows. No DOSBox. Peter Kmet's port did the heavy lifting: Ghidra decompilation → ~60k lines of clean C11 + SDL3. Builds in seconds, ships in a 1.2 MB zip.
1
21
Konstantinos Zagoris retweeted
Passenger v0.4.0: .NET MAUI and mobile apps. Run, debug and Hot Reload on Android, an iOS simulator or your Mac, with a live XAML preview. Plus screen readers, themes and Vim mode. Still free and MIT. passenger-ide.net/?v=0.4.0
3
10
1
64
32,954
Τρελά πράγματα με τον Ολυμπτιακό στο μπάσκετ!
9
I am going back and forth between dotnet c# AOT/ReadyToRun (R2R) versus rust. I hate the build times and the storage bloat.
89ms - OpenCode Rune 830ms - OpenCode (time to launch with UI ready) The rust port is going well
23
Yes I tried to a project, it was amazing
windows sandbox is really good 👍 they cooked with this
13
Konstantinos Zagoris retweeted
Starlink saves lives
BREAKING: Greece’s government is using Starlink to support a railway safety system that warns of potential train collisions. Starlink sends live train data to the control center, including through mountainous areas without mobile coverage. • Monitoring equipment installed on 134 locomotives. • GNSS-HEPOS positioning pinpoints trains with accuracy of up to 5 centimeters. • Location updates every second. • A 24/7 control center receives automatic collision-risk alerts so operators can intervene.
938
1,727
125
13,225
1,381,782
Konstantinos Zagoris retweeted
i built gpt-2 in pure assembly. 124m params. zero libc calls. the tokenizer, matmuls, attention, softmax, even exp(): all arm64 asm. ~100 tok/s on a single m1 core. 4 kb of machine code. output matches pytorch token for token.
84
89
16
1,366
74,554
That is so cool!
we're building a fully native disassembler that doesn't suck
16
Konstantinos Zagoris retweeted
A lot of people don't realize that Windows has a built-in feature called Windows "Sandbox" that boots up a brand new virtual Windows machine in seconds. So I made an MCP server so you can test your apps inside a throwaway machine in seconds. github.com/shanselman/sandbo…
95
301
23
1,912
89,726
Konstantinos Zagoris retweeted
This work is simple, clear, compelling, but embellished. I first found it shocking, the notion that a model can natively understand neural network weights and productively edit them! That's really not what's happening, & many here are annoyed. BUT, it's still notable & worth understanding. I've done a bit of analysis & auditing, here are some thoughts: 1/ This paper does *not* show an agent can edit its weights ala RSI. It does *not* show a model can edit in new capabilities. It DOES show that a frontier model can remove "bugs" (reasoning loops), using the same ablation technique researchers have used to remove safety refusals (Exp 8 - Qwen). So yes, renewed concern about frontier LLMs getting access to their own weights & editing safety/CBRNE/alignment features. 2/ This paper also does *not* show that an agent can "natively" read, deeply understand, and fix model weights. What is happening is that the model can cleverly deduce the same things that mech-inturp researchers do and fix them in mostly ham-fisted ways. Still cool, but not as groundbreaking. Evidence in thread below...
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
12
50
12
379
34,571
Konstantinos Zagoris retweeted
There's a lot going on in my GPU. I'm making a GPU Taskman to get insights to where my GPU memory is going. PRs welcome
34
47
11
553
32,293
Wild
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2
16
Konstantinos Zagoris retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,368
7,258
5,755
55,918
10,084,859
Proxenos now has a desktop app. Built with Kotlin and Compose Multiplatform. Open source, MIT licensed. 👇
Waiting for OpenAI DevDay and the ChatGPT + Work merge? Out of coding-agent credits? Check my Proxenos: ChatGPT accesses your repo, so you keep working from the chat without spending credits. The tech: secure tunneling. No open ports, no public URL.
1
1
54
🧰 Tools: see which tools ChatGPT gets for each folder, and try any of them yourself before ChatGPT does. 📡 Activity: watch ChatGPT's calls as they happen. A running command shows its output live, and you can stop it with one click. Anything that needs your attention is flagged
1
13