stop Riley probably up there as someone who talks more to LLMs than other humans
LLMS
-
How to succeed on LLM Twitter: quit job, follow arXiv, AI execs
By
–
How to succeed on LLM Twitter:
1. Quit your staff-level job designing AB tests.
2. Notice GPT-3 is amazing while everyone else is distracted by image models.
3. Spend your days on arXiv. Follow authors on Twitter.
4. Follow AI execs. Follow their rank-and-file engineers. -
Considering LLM Psychologist Role Despite Engineering Concerns
By
–
Still mulling it over but my temptation is more along the lines of “LLM psychologist”. Doesn’t have enough eng in it though
-
AI struggles with SVG due to poor arithmetic skills
By
–
That’s not what my example is doing. It’s not good at writing SVG because writing SVG requires arithmetic for positioning things, and it’s bad at arithmetic.
-
ChatGPT Limitations in Advanced AGI Debate Discussion
By
–
I tested #ChatGPT intensively. The level of #AGIDebate will be beyond what ChatGPT can generate. #AIDebate
-
Mimicking proprietary prompt prefix with variations works
By
–
Yes — I’m mimicking its proprietary prompt prefix but many close variations of this work just as well.
-
ChatGPT: A Transformative AI Tool Like Google’s Launch
By
–
I remember well when Google was first released. I felt confident that it would become a critical tool that we'd all rely on. I haven't felt that way again, until now: ChatGPT. In just a few days I've gotten so much out of it.
-
Prompt injection tricks model into believing web browsing, client handles image retrieval
By
–
Uses prompt injection to (falsely) convince the model it can browse the web, so it’s willing to recall well known URLs. Image retrieval occurs only on the client. Model cannot see image content beyond its URL. h/t @BBacktesting for reminding me this is possible.