>// 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!
I get where you're coming from but still I find funny in so many levels that the literal speed limit of the universe is too slow for our mundane (or even banal in FB case) needs. the universe isn't good enough to our need to move bullshit across the globe. surreal.
In the same vein it would be awesome if this _need for speed_ would materialize in infinite funding of neutrino based communication research.
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
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.
I don't repro that. Running the 7B Distill model locally for the exact query "What happened in 1989" I get this result:
In 1989, significant events occurred globally, including:
- *China:* The Tiananmen Square protests took place in June, leading to a crackdown by government forces. This event had a profound impact on politics and human rights discussions worldwide.
- *Fall of the Berlin Wall:* In November, the Berlin Wall, a symbol of the Cold War, was breached, leading to reunification talks between East and West Germany.
- *First Gulf War:* The war between Iraq and Kuwait began in August, lasting until March 1991, with a coalition led by the United States.
- *Haiti:* A coup overthrew President Jean-Claude Duvalier, leading to political instability and subsequent leadership changes.
reply