(This post is intended for my personal blog. Thank you.)
One of the dominant thoughts in my head when I build datasets for my training runs: what our ancestors ‘did’ over their lifespan likely played a key role in the creation of language and human values.[1]
“Mother” in European Languages
I imagine a tribe whose members had an approximate of twenty to thirty-five years to accumulate knowledge—such as food preparation, hunting strategies, tool-making, social skills, and avoiding predators. To transmit this knowledge, they likely devised a system of sounds associated with animals, locations, actions, objects, etc.
Sounds related to survival would have been prioritized. These had immediate, life-and-death consequences, creating powerful associations (or neurochemical activity?) in the brain. “Danger” or “food” would have been far more potent than navigational instructions. I think evolution manages those actions that gets used repeatedly. The constant reinforcement of survival sounds and their associated actions (as enabled by our genetics[2]) likely built the foundations of language. I think stories[3] were used to simulate world interactions, necessitating a coherent string of sounds—where an abstracted pattern emerges.
What I am trying to describe here as the process of passing information down to the next generation is what I now refer to as a Intergenerational Knowledge Transfer (IKT). Finally, I believe that viewing evolutionary learning as a sequence of IKTs, where each IKT can be considered as a sample[4] in a dataset, is not a bad theoretical experiment to wrestle with.[5]
Why do I believe that datasets may serve as a pathway for an evolutionary learning? I speculate that our world can be simulated in a capable language model and if we can strategically create/construct/curate a dataset or a series of datasets—aligning language models to our values is possible.
I should write further into why I believe that “stories serve as a universal structure for information” next week. However, to briefly explain: I think that the pattern of a setup, conflict, and resolution, commonly known as a three-act narrative, can encapsulate any complex idea—even the simulation of a world...
In order to align with the IKT sample I’m referencing in this post, the sample must consist of a collection of related words that are repeatedly elaborated upon, with the aim of delineating a single, intricate pattern.
Intergenerational Knowledge Transfer (IKT)
(This post is intended for my personal blog. Thank you.)
One of the dominant thoughts in my head when I build datasets for my training runs: what our ancestors ‘did’ over their lifespan likely played a key role in the creation of language and human values.[1]
I imagine a tribe whose members had an approximate of twenty to thirty-five years to accumulate knowledge—such as food preparation, hunting strategies, tool-making, social skills, and avoiding predators. To transmit this knowledge, they likely devised a system of sounds associated with animals, locations, actions, objects, etc.
Sounds related to survival would have been prioritized. These had immediate, life-and-death consequences, creating powerful associations (or neurochemical activity?) in the brain. “Danger” or “food” would have been far more potent than navigational instructions. I think evolution manages those actions that gets used repeatedly. The constant reinforcement of survival sounds and their associated actions (as enabled by our genetics[2]) likely built the foundations of language. I think stories[3] were used to simulate world interactions, necessitating a coherent string of sounds—where an abstracted pattern emerges.
What I am trying to describe here as the process of passing information down to the next generation is what I now refer to as a Intergenerational Knowledge Transfer (IKT). Finally, I believe that viewing evolutionary learning as a sequence of IKTs, where each IKT can be considered as a sample[4] in a dataset, is not a bad theoretical experiment to wrestle with.[5]
Why do I believe that datasets may serve as a pathway for an evolutionary learning? I speculate that our world can be simulated in a capable language model and if we can strategically create/construct/curate a dataset or a series of datasets—aligning language models to our values is possible.
I’m still trying to wrap my head around the kind of capabilities or genetics is necessary that enables language learning and speech control.
(This might be a relevant reading: The evolutionary history of genes involved in spoken and written language: beyond FOXP2.)
I should write further into why I believe that “stories serve as a universal structure for information” next week. However, to briefly explain: I think that the pattern of a setup, conflict, and resolution, commonly known as a three-act narrative, can encapsulate any complex idea—even the simulation of a world...
In order to align with the IKT sample I’m referencing in this post, the sample must consist of a collection of related words that are repeatedly elaborated upon, with the aim of delineating a single, intricate pattern.
I experimented on this by sequentially layering ten datasets to reperesent an evolutionary approach to ethical alignment, there is notable improvements on GPT2XL’s robustness to jailbreaks (JB) - negating up to 67.8% of the attacks. Also, the same model was able to solve a theory of mind task 72 out of 100 times. These are tests that foundation models fail a lot (see JB: 1, 2, 3; ToM) .