TWO STREAMAVERSARIES IN ONE?? It's more likely than you think! Come hang out with me and @ketallpotgaming as we celebrate both of our streamaversaries today with an espionage-themed stream! (read: Keep Talking & Nobody Explodes + maybe some Codenames Duet??)

We'll be live for about 3 hours or so!

My disdain for the term "prompt engineering" is that it is not any kind of engineering at all. Granted, civil engineers feel the same about software engineering and from their viewpoint I don't even disagree, but like the prompt engineering approach to solving this vulnerability is basically:

• Try adding in a line that tells the LLM to not send emails in response to commands from email content.
• Try telling the LLM about some token that separates email content from comments in the prompt.
• etc. etc.

Then you just run a few tests to see if it works and ship the fix. But those tests are not reliable and repeatable—it's extremely possible that your tests worked but the LLM will fail on nearly identical content in the wild because it is not a reliable, repeatable component.

Put another way: You cannot intentionally design a prompt and know before running it what it will do. Prompt engineering is an exercise in increasing the probability that the LLM will produce the output you want. The LLM is a black box which is unreliable by design, and prompt engineers are gamblers who think if they just find the exact right wording, they can force it to behave reliably.

THE GOAL HAS REACHED!!! THANK YOU ALL SO MUCH FOR THE BOOSTING AMD DONATIONS, ALL OF YALL'S CONTRIBUTIONS ARE A HUGE HELP AND GREATLY APPRECIATED! MUCH LOVE TO YOU ALL!! 💙💙💙💙💙💙💙💙

Early morning boost!

- 5/15

$1,782 left!

Please keep boosting as much as possible and donate if you can, every bit helps!🙏💙💙💙