Karim Jedda (@KarimJDDA) header
Karim Jedda (@KarimJDDA) profile picture

Director of Engineering @ Parity Technologies

🥔
Joined February 2012
Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)Photo by Karim Jedda (@KarimJDDA)
Try it with the MCP, it's excellent
LibreOffice actually works 365 days a year. Just saying.
183
Libreoffice MCP with Claude works very well, even with complex spreadsheets/docs.
3
302
Karim Jedda retweeted
*sshole is out if you run sshd on alpine, openwrt or any musl box with password auth on: update now official writeup: sshhole.com
86552c7e1e5d46882844cffabb44d454129ff22927f13797b151c9db4519d47d
188
890
446
5,449
1,572,319
Excellent AI-era swes minimize the total cost and time required to reach a result verified to the level the problem demands either using LLMs or no LLMs at all.
1
3
274
Syntax mastery is now a commodity so focus on three things: systems architecture, precise and articulate specification and rigorous verification and testing. Not much different than the pre-AI era :)
1
1
125
So in some sense the LLMs helped us come full circle to remind us that the fundamentals we've been ignoring in favor of "coding" are actually the most important and crucial parts of engineering.
1
86
Karim Jedda retweeted
I'm Marc. 12 years in ops, now building with AI Barcelona born, London based Looking to connect with more founders and builders Let's connect
216
5
1
178
4,396
Karim Jedda retweeted
Releasing the model weights of Kimi K3.1 Pro: huggingface.co/moonshotai/Ki… We'll keep advancing open intelligence.
405
852
486
8,799
1,599,022
Everything is open source now
1
2
1
16
1,458
Need a Claude skill to turn influencer videos into "videos that respect my time"
3
201
Karim Jedda 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.…
2,367
7,262
5,753
55,939
10,053,266
Karim Jedda retweeted
Vibe coding is just coding now.
190
208
32
4,962
116,857
At this point it might be simpler to just publish the curated/filtered down datasets and let clients mix and match how they please. 😁
1
2
34
7,334
Karim Jedda retweeted
Good progress in the last few weeks ! And now the weights
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity. 💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis. 🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others. Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it. Read more from our team and customers 👇:
48
72
3
973
28,908
Karim Jedda retweeted
AWWWWOOOOOOOGAAAAAAA 9.8 severity use-after-free vulnerability in the kernel’s IPv4 TCP stack just landed Time to patch! ubuntu.com/security/CVE-2026…
97
242
99
2,898
421,574
Karim Jedda retweeted
Generated by the insanely powerful Echo-3 world model. Rendered by the open source PlayCanvas Engine. 🤝
🌍 Introducing Echo-3, a new world model enabling the most accurate reconstructions of real spaces to date! From a quick phone video of my daughter’s room, Echo-3 built a 3DGS model and restyled the whole house with her favorite fairy tales 🚀✨. Get the app and try it out!
1
14
133
7,643
What, @X adding 402 payments? 👀
1
1
333