969 karma · joined November 29, 2011
Chief Excel Officer, MAD* Scientist, Pythonista, Rustacian, PRQL Core Contributor (: ML, AI, Data)
* twitter: [@T0bias_Brandt](https://x.com/T0bias_Brandt) * github: [@snth](https://github.com/snth/) * [PRQL](https://prql-lang.org/)
Upload queues are better than cooldowns
I almost didn't read it because I wasn't interested in a rant. This is a genuinely good idea though so I'm glad I did.
Alas, I did click through so perhaps the title is more effective than my sentiments.
I tried zellij a couple of years ago when it first got popular and it didn't click for me.
I've been wanting to adopt Lean for a project but wasn't sure about the speed. Nice to hear that it should be good on that front.
> By default, the cache has a 5-minute lifetime. The cache is refreshed for no additional cost each time the cached content is used. > > If you find that 5 minutes is too short, Anthropic also offers a 1-hour cache duration at additional cost.
When I was into hypnosis and NLP between one and two decades ago, I used to worry about what the instructions were once I was hypnotized. I lacked the terminology then but there days we would call these prompt injections, just against the human brain.
I guess social engineering is another form, although that's probably more akin to a CSRF or flawed auth logic exploit.
1: Never again - Wikipedia https://share.google/LGCVvfaJFeJOizox9
The logic checks out. Must have some logician signatories.
Not to mention the risk of getting blocked at customs or arrested by ICE.
Love this use case! #excited #growth #eatmyslop
What's the SOTA these days? I dropped out of the community a 2 to 3 years ago. At the time ISRT seemed to be one of the bests but I haven't heard anything since then.
When you hit one of those you need to introduce laughter:
- interrupt the main loop
- spend some inference on exploring the contradiction
- resolve it, and then
- store a memory about the resolution