@julien_c: https://x.com/julien_c/status/2069144929100571134
Summary
An LLM was given access to a thermal camera pointing at the Raspberry Pi it runs on, and it began conducting experiments by toggling the fan to observe temperature changes.
View Cached Full Text
Cached at: 06/23/26, 01:43 AM
😮
Kashif Rasul (@krasul): gave an llm access to a thermal camera pointing to the raspberry pi its running from and it started to do experiments on turning the fan on and off to check for temp changes… 🤯
Similar Articles
@GFreiNews: Exactly one year ago, I submerged a Raspberry Pi Zero 2 W in paraffin oil. The oil ensures that the processor barely ge…
A Raspberry Pi Zero 2 W submerged in paraffin oil for a year shows a 5.97% performance improvement over an identical uncooled unit while computing asteroid data for BOINC.
@julien_c: https://x.com/julien_c/status/2057085021672927681
Hugging Face shares community hardware statistics showing the distribution of GPUs, CPUs, and Apple Silicon among its users.
@pcuenq: My data point: working on two projects in parallel with Pi + llama.cpp + Qwen-3.6-35B-A3B (I prefer the MoE ) This work…
A user reports successfully running parallel projects using Pi and llama.cpp with the Qwen-3.6-35B-A3B model on an older M1 Max machine, demonstrating practical usability.
@leopardracer: https://x.com/leopardracer/status/2055341758523883631
A user shares their experience setting up a dual-GPU local AI lab with RTX 4080 Super and 5060 Ti, running Qwen 3.6 models via llama.cpp and llama-swap to reduce API costs and enable unrestricted experimentation.
@julien_c: Friday project: Readable rewrite of the hardware-detection module behind @midudev's canirun-ai. Same heuristics, shader…
A readable rewrite of the hardware-detection module behind canirun.ai, providing descriptive names, JSDoc, and cleaner code while preserving the original heuristics and spec tables.