gen3

Looks good. I normally package a webui up with vite and serve that but I'll keep this in mind

On the repebble compare chart the round is marked as having both a speaker and mic, that’s incorrect right?

>// Classify incoming emails using Workers AI const { score, label } = env.AI.run("@cf/huggingface/distilbert-sst-2-int8", { text: message.raw" })

This is neat but be careful using an LLM to parse email content. The demo is a BERT model which is a good but I can see how someone might swap this without realising the implications

Also really nice to see emails from workers, its something I have wanted for a while!

You’re pretty close to Texas tech hubs, plus Meta was able to convince them to pass Louisiana Act No 730 so they save a ton on capex

The speed of light is incredibly slow and data through a wire is even slower. Proximity is worth something

Incredibly cool work, and a great primer on diffusion

Trade becomes easier. Metaphorically pushing the bar across the room.

Countries also keep cash funds at the NY Federal reserve too

Outstanding article, don't skip the youtube videos!

Very cool work! I really like being able to see the blocks and directly interact with them. It's nice to feel out how the ECC works. I can see myself using this to draw custom QR codes in the future!

My understanding is that with most current reactors there is an inner loop that is constantly recirculating (reactor to turbine) that does not leave containment. This goes through a heat exchange with other water to jettison waste heat from the system. This waste heat can be something like taking water from a river and ejecting it back into the river, just slightly warmer.

I’m curious how much using less water actually matters. It’s not like the jettisoned water is dangerous or radioactive

Yes, but the AI was talking about implementing output sanitization in its proposed solutions.

> An alternative approach is to store the raw markdown content and handle rendering and sanitization in the browser:

You could move the sanitation to the front end securely, it would just need to be right before render (after fetching the data to the browser). Some UI libraries do this automatically (like React) and the dompurify can run in the browser for this task.

It could have done a better job outlining how to do it properly

The local models do contain censoring. Running "What happened in 1989" returns "I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses." on 32b

Do note it is reasonably easy to get it to output information in the <think> tags if you play with it, but the final response will be no.

Where can I read more about UNICOR doing some of the redesign work?