Do you also have estimates of the fraction of resources in our light cone that we expect to be used to create optimised good stuff?
Maybe the use of prompt suffixes can do a great deal to decrease the probability chatbots turning into Waluigi. See the "insert" functionality of OpenAI API https://openai.com/blog/gpt-3-edit-insert
Chatbots developers could use suffix prompts in addition to prefix prompts to make it less likely to fall into a Waluigi completion.
Indeed, empirical results show that filtering the data, helps quite well in aligning with some preferences: Pretraining Language Models with Human Preferences
What about the impact of dropout (parameters, layers), normalisation (batch, layer) (with a batch containing several episodes), asynchronous distributed data collection (making batch aggregation more stochastic), weight decay (impacting any weight), multi-agent RL training with independent agents, etc.
And other possible stuff that don't exist at the moment: online pruning and growth while training, population training where the gradient hackers are exploited.
Shouldn't that naively make gradient hacking very hard?
We see a lot of people die, in the reality, fictions and dreams.
We also see a lot of people having sex or sexual desire in fictions or dreams before experiencing it.
IDK how strong this is a counter argument to how powerful the alignment in us is. Maybe a biological reward system + imitation+ fiction and later dreams is simply what is at play in humans.
Should we expect these decompositions to be even more interpretable if the model was trained to output a prediction as soon as possible? (After any block, instead of outputting the prediction after the full network)
Some quick thoughts about "Content we aren’t (yet) discussing":
SL (Cloning) is more important than RL. Humans learn a world model by SSL, then they bootstrap their policies through behavioural cloning and finally they finetune their policies thought RL.
Why? Because of theoretical reasons and from experimental data points, this is the cheapest why to generate good general policies…
The learned values known by the previous generation.
Some instrument goals are learned as final goal, they are “internalised”.
We have here 3 level of rewards function:
Hardcoded in our body
Optimisation process creating it: Evolution
Not really flexible
Almost no generalization power
Called sensations, pleasure, pain
Learned through life
Optimisation process creating it: SL and RL relying on biological rewards
Flexible in term of years
Medium generalization power
Called intuitions, feelings
Shard theory may be explaining only this part
Decided upon reflection
Optimisation process creating it: Thinking relying on the brain
Flexible in term of minutes
Can have up to very high generalization power
Called values, moral values
In short, to get more utility OOD.
A bit more details:
Because we want to design policies far OOD (out of our space of lived experiences). To do that, we know that we need to have a value function|reward model|utility function that generalizes very far. Thanks to this chosen general reward function, we can plan and try to reach a desired outcome far OOD. After reaching it, we will update our learned utility function (lvl 2).
Thanks to lvl 3, we can design public policies, dedicate our life to exploring the path towards a larger reward that will never be observed in our lifetime.
This could explain why most philosophers can support scope sensitive values but never act on them.
You can see the sum of the votes and the number of votes (by having your mouse over the number). This should be enough to give you a rough idea of the ration between + and - votes :)
If you look at the logit given a range that is not [0.0, 1.0] but [low perf, high perf], then you get a bit more predictive power, but it is still confusingly low.
A possible intuition here is that the scaling is producing a transition from non-zero performance to non-perfect performance. This seems right since the random baseline is not 0.0 and reaching perfect accuracy is impossible.
I tried this only with PaLM on NLU and I used the same adjusted range for all tasks:
[0.9 * overall min. acc., 1.0 - 0.9 * (1.0 - overall max acc.)] ~ [0.13, 0.95]
Even if this model was true, they are maybe other additional explanations like the improvement on one task are not modeled by one logit function but by several of them. A task would be composed of sub-tasks each modelizable by one logit function. And if this make sense, one could try to model the improvements in all of the tasks using only a small number of logit curves associated to each sub-tasks (decomposing each tasks into a set of sub-tasks with a simple trend).
(Also Gopher looks like less predictable and the data more sparse (no data point in the X0 B parameters))
This is a big reason for why GPT4 is likely not that big but instead trained on much more data :)