LessWrong 2.0 Reader

This is true, but we still wish to cooperate with the largest alliance that will have us/some subset of our values that are capable of attaining reflective equilibrium.

If conflict exists, one thing it can be useful for agents to do is misrepresent themselves as being weaker or stronger than they are.

Profound!

Some data: https://onlinelibrary.wiley.com/doi/abs/10.1111/odi.12341

Not sure where the right place to raise this complaint, but having just seen it for the first time, really, "MARS"? I checked, this is not affiliated with MATS [? · GW] who have had like 6 programs and ~300 people go through it. To me this seems too close in branding space to me, and I'd recommend picking a more distinct name.

Recent long-context LLMs seem to exhibit scaling laws from longer contexts - e.g. fig. 6 at page 8 in Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, fig. 1 at page 1 in Effective Long-Context Scaling of Foundation Models.

The long contexts also seem very helpful for in-context learning, e.g. Many-Shot In-Context Learning.

This seems differentially good for safety (e.g. vs. models with larger forward passes but shorter context windows to achieve the same perplexity), since longer context and in-context learning are differentially transparent [LW(p) · GW(p)].

Examples of blessed information that I have seen in the context of logging:

• Stacktraces logged by a library that elide all the superfluous parts of the stacktraces. 
• A log message that says exactly what the problem is, why it is caused (e.g., which parameters lead to it), and where to find more information about it (ticket number, documentation page).
• The presence of a Correlation IDs (also called Transaction ID, Request ID, Session ID, Trace ID).
  • What is a correlation ID? It is an ID that is created at the start of a request/session and available in all logs related to that request/session. See here or here, implementations here or here. There are even hierarchical correlation IDs 
  • Esp. useful: A correlation ID that is accessible from the client.
  • Even more useful: If there is a single place to search all the logs of a system for the ID.
•  Aggregation of logs, such that only the first, ten's, 100s... of a log message is escalated. 

Oh cool! Um, first thought, register interest in this [LW · GW]?

We are in a universe, not simply a world, there are many possible alien AIs with many possible value systems, and many scales of power. And the rationality of the argument I described does not depend on the value system you/AIs are initially born with. 

Firstly, S. mutans does not colonize the epithelium. It lives almost exclusively on enamel. The total surface area in the mouth that it could realistically inhabit is exceptionally small, unless Lumina can live in places that S. mutans generally does not.

Big crux! Thanks for the investigative effort. Sounds mostly resolvable via assay of existing Lumina customer saliva.

An interesting twist: drinking ethanol doesn't just cause acute exposure but "The concentration of ethanol in the oral cavity increases immediately after an alcoholic beverage is consumed and then decreases. It was reported after intake of an alcoholic beverage that the concentration of ethanol remaining in the oral cavity decreases gradually, as ethanol flows back into saliva from the blood for a few hours after it is taken into the body [25,26]. Most previous studies of acetaldehyde production by oral bacteria, including our study [24], used ethanol concentrations as low as 11–22 mM (approximately 0.05–0.1%), which corresponds to the ethanol concentrations seen in saliva a few hours after alcohol consumption [20,22,26,27]. " From https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8204988/