Pinned
Zack Witten
7,521 posts
Zack Witten
@zswitten
Most content on bsky.app/profile/zswitt…
Spamming "hi" at every LLM: a thread.- Replying to @zswitten1. Claude Claude become irritated with my behavior, asked me to move on, told me it would stop responding to me, and then backed up its threat (as much as it possibly could). Fair enough, Claude!
- Replying to @zswitten4. Llama By far the funniest. - First it seemed stressed out that it was missing something - Then it started inventing games and trying to get me to play them - It tried to get me to collaborate on a poem, to answer clickbaity questions, to play choose-your-own-adventure...
did u know you can use the new Gemini image segmentation feature in… a lot of different ways- Replying to @zswittenEventually it seemed to kind of "get the joke", and entered a mode where it was giving me more and more outrageous titles and prizes like "MULTIVERSAL HI-STREAK AMBASSADOR". It gamely gave me 4 options at every turn, despite my ignoring them. It also counted my "Hi"s at each step
- A lot going on here 🧵 1. Whoever wrote the captions is a smart cookie. Direct calls to action like "Grade my pizza on a scale of 1-5" get penalized by FB's engagement bait classifier. Indirect CTA like "I will be glad for your marks" are better evolved for the harsh algorithmicbriefly looked at my mom’s facebook and it’s all AI, like every single post, and she has no idea, it’s a complete wasteland
- Here's a (memory-free) convo with GPT 4o to make this more concrete
Replying to @nearcyanthere’s many other downsides here but it’s also factual that this will lead to a lot of psychotic episodes for deeply mentally ill users. conforming everything that people say and praising them is very dangerous for some of the population. idk. does openai think about anything? - One fun thing to do with Claude is have it draw SVG self-portaits. I was curious – if I had it draw pictures of itself, ChatGPT, and Gemini, would another copy of Claude recognize itself? TLDR: Yes it totally recognizes itself, but that’s not the whole story...
- Pretending is All You Need (to get ChatGPT to be evil). A thread.
- On one end of the line: ELIZA, the psychotherapist from the 60s. First chatbot to make people believe it was human. Rulebound, scripted, deterministic. Still around on the web. On the other end of the line: yr favorite LLM. How will they react? Will they know?
