Introducing spikee, an open-source toolkit for testing LLM applications against prompt injection attacks that can lead to exploitation—like data exfiltration, XSS, and resource exhaustion. Easily create custom datasets to match your specific use cases. spikee.ai

We spent the last few months overhauling our logistics infrastructure around refurbishment, and today we launched a broad set of refurbished products into the Framework Outlet. We'll be able to turn around customer returns into refurbs faster now too!

Intel Arc Pro B70 (32GB) for Local LLMs: llama.cpp (SYCL/Vulkan), vLLM (Intel LLM Scaler) Benchmarks youtu.be/MnGLqo5cuGQ

In this video, I look at what works when running coding agents locally on Strix Halo and Radeon R9700. I cover pi and opencode running Qwen 3.6, and SWE-bench mini benchmark results: youtu.be/JyS8A-5LIY8

youtu.be/MI0Pm1d6YF4 MTP can accelerate LLM inference 2x, especially for coding agents. This video covers what MTP is and the performance improvements you can expect for Qwen 3.6 on AMD Strix Halo & Dual Radeon 9700.

My two cents on how to interpret the Mozilla / Mythos findings. linkedin.com/pulse/donato-ca…

Salerno airport is so disorganised, not able to handle border control for the ONLY flight landing. Making people wait 30 minutes to go through border control when there is only one flight

youtu.be/h6bK1-EX42A In this video I experiment and benchmark the MI50 32GB GPU with LLM inference using llama.cpp and vLLM and copare it with AMD R9700 and Strix Halo.

The new Framework Laptop 13 Pro is a thing of beauty! Thank you @FrameworkPuter for sending over a pre-release engineering sample to try out. Loving it, Linux works like a charm, haptic track pad is great, keyboard and screen also feel very premium!

It finally happened to me, a coding agent nuked 1TB of models because I was distracted and trusted it, I did not check the code. LLMs are very willing to hide destructive commands everywhere they can, sooner or later this will happen to anyone :(

Hi all, I decided to publish a channel update as it's been almost 2 months since my last video. Lots of work behind the scenes maintaining the toolbxoes and teow new series starting in May on Local AI Agents and Refurbished GPUs: youtu.be/0mXYp6d0yjw

DC ☠️ SG1 is in the books and it was a blast! 🚀 🚀🚀

Somehow sales haven't slowed down over the last few days, and we're now into Batch 11. Also, the % of Ubuntu pre-built configurations is continuing to climb!

One week after opening pre-orders, these are still selling extremely fast. We're now into Batch 10, which is our last August batch. We're going to do everything we can to scale manufacturing capacity to build these faster too!

Consequence of falling victim to the Normalization of Deviance in AI Guardrails and trusting model safeguards training by ai labs are not a replacement for security, and well, also regular engineering best practices and principles. Trust No AI embracethered.com/blog/posts…

The New Linux Kernel AI Bot Uncovering Bugs Is A Local LLM On @FrameworkPuter Desktop @AMD @AMDRyzen AI Max Greg Kroah-Hartman has shown off his "gkh_clanker_t1000" setup that's been helping uncover Linux bugs. phoronix.com/news/Clanker-T1…

labs.reversec.com/posts/2026… We have been busy implementing support for multi-turn attacks like Crescendo, Echo Chamber and GOAT into spikee, making them easy to tweak and customise during security assessments of LLM applications. 📷

The creator of Linux, Linus Torvalds, just unknowingly obliterated Elon Musk in one sentence:

True story 🤣

I love Geoff. But he understands even less than Dario about the effects of technological revolutions on the labor market. Again, don't listen to AI scientists, as brilliant as they might be, and even less to AI CEOs, as successful as they might be, for questions of labor economics. Listen to reputable economists who have studied these things like @Ph_Aghion , @DAcemogluMIT , @erikbryn , @amcafee , @davidautor , etc.

Just a thought: did they compare Mythos vs the recent nerfed version of Opus (with shorter thinking chains etc) or the full version? Is Mythos mostly just a version of Opus with training that removes refusals on some hacking topics?