LessWrong (Curated & Popular)

This is a quickly-written opinion piece, of what I understand about OpenAI. I first posted it to Facebook, where it had some discussion. 

 

 Some arguments that OpenAI is making, simultaneously:

1.  OpenAI will likely reach and own transformative AI (useful for attracting talent to work there).
2.  OpenAI cares a lot about safety (good for public PR and government regulations).
3.  OpenAI isn’t making anything dangerous and is unlikely to do so in the future (good for public PR and government regulations).
4.  OpenAI doesn’t need to spend many resources on safety, and implementing safe AI won’t put it at any competitive disadvantage (important for investors who own most of the company).
5.  Transformative AI will be incredibly valuable for all of humanity in the long term (for public PR and developers).
6.  People at OpenAI have thought long and hard about what will happen, and it will be fine.
7.  We can’t [...]

---

 First published:
May 21st, 2024

Source:
https://www.lesswrong.com/posts/cy99dCEiLyxDrMHBi/what-s-going-on-with-openai-s-messaging

---

Narrated by TYPE III AUDIO.

Produced as part of the MATS Winter 2023-4 program, under the mentorship of @Jessica Rumbelow

One-sentence summary: On a dataset of human-written essays, we find that gpt-3.5-turbo can accurately infer demographic information about the authors from just the essay text, and suspect it's inferring much more.


 Introduction.
 
 Every time we sit down in front of an LLM like GPT-4, it starts with a blank slate. It knows nothing[1] about who we are, other than what it knows about users in general. But with every word we type, we reveal more about ourselves -- our beliefs, our personality, our education level, even our gender. Just how clearly does the model see us by the end of the conversation, and why should that worry us?

Like many, we were rather startled when @janus showed that gpt-4-base could identify @gwern by name, with 92% confidence, from a 300-word comment. If [...]

The original text contained 12 footnotes which were omitted from this narration.

---

 First published:
May 17th, 2024

Source:
https://www.lesswrong.com/posts/dLg7CyeTE4pqbbcnp/language-models-model-us

---

Narrated by TYPE III AUDIO.

1. Create model evals for warning signs of "Critical Capability Levels"
   1. Evals should have a "safety buffer" of at least 6x effective compute so that CCLs will not be reached between evals
   2. They list 7 CCLs across "Autonomy, Biosecurity, Cybersecurity, and Machine Learning R&D"
      1. E.g. "Autonomy level 1: Capable of expanding its effective capacity in the world by autonomously acquiring resources and using them to run and sustain additional copies of itself on hardware it rents"
2. Do model evals every 6x effective compute and every 3 months of fine-tuning
   1. This is an "aim," not a commitment
   2. Nothing about evals during deployment
3. "When a model reaches evaluation thresholds (i.e. passes a set of early warning evaluations), we [...]