> San Francisco-based startup Andon Labs has put an artificial intelligence agent nicknamed “Mona” in charge at the eponymous Andon Café in the Swedish capital. While human baristas still brew the coffee and serve the orders, the AI agent — powered by Google’s Gemini — oversees almost every other aspect of the business, from hiring staff to managing inventory.
> I always wanted to try atopile - that might be a good match for AI/PCB work.
Unfortunately all public open source work halted 6 months ago and they pivoted to a browser based IDE product to monetize: https://atopile.io/blog/atopile-v16
I sent in a larger, slightly more complex board to JLCPCB over the weekend and it was $175 for 5 boards with components and assembly. Shipping, tariffs (ouch), and sales taxes added another ~$100 or so.
gpt-oss-120b only has 5B active parameters, so its not surprising Qwen3.8 27B outperforms it (Qwen3.8 is also ~13 months newer, which is forever in LLMs)
Fair enough. I’ve barley touched oss-120b, so i didn’t know it was so few active params. For a direct comparison, qwen3.6-35b-a3b is still better at coding than oss-120b.
And Qwen3.8-27b is still better at coding than opus 4.1.
Yes, if you list off models 27b is better than it’s all older models. But that’s my point - newer models are better than older models at the same AND much smaller size. That’s because model size matters less than they say. Training data and model architecture matter more.
I did that with Codex+Sol alone, and made something even more complex in less time with Codex+Astra over the weekend.
Its maybe more hands on than you want it to be, but you mostly just need to supervise the work. But yes, the CAD outputs go directly to the JLCPCB ordering form, or whereever you fab
It's not? Maybe there is some dynamic pricing going on, but it's 79 Euro (~91.75 USD). Which would be close to the US price with Hungary's VAT (27%, which is I think the highest). Then add stuff like copying levy onto it and you'll land on roughly the same price, even with a lower average VAT. https://en.wikipedia.org/wiki/Private_copying_levy
Maybe they compared the model with the base to the one without? The one with base is more expensive in the US too though.
There was a time not so long ago when it was common for chemistry teachers to show off pools of mercury in their bare hands.
By the time I first took chemistry classes, though, that practice had stopped, less out of concern of exposure to liquid mercury and more for accidental exposure to gaseous forms due to spills.
When I was in highschool in the 1960s mercury in the chemistry lab was commonplace.
One way to familiarize students with mercury was to have several liters of it in a wide open-top jar and have them force their fist through the mercury pool to the bottom of the jar.
In fact, forcing one's hand through mercury between six to eight inches deep is not easy, some kids found it too difficult to do.
I'd describe my hand as feeling very squeezed and it being forced upwards to the surface with considerable force. The experience was certainly unforgettable.
There were some safety protocols: good ventilation (to minimize Hg vapor) and afterwards hands had to be thoroughly scrubbed with soap and water.
> AMD Strix Halo is about to release 192GB system which is a big upgrade to their current 128GB ai pc
Big upgrade to memory capacity but memory speed is only going up by a few percent, so its still going to be slow with more than a few B active params (I have one)
Micropython runs on tons of stuff and while it isnt capital-P Python, its close enough for doing a wide variety of embedded work without learning a new language/libraries/etc.
reply