Kerry Friend
@kerryfriend
Joined Feb 16, 2022
48
Following
163
Followers
Learns #Human Behavior #Design #Network Effect #Philosophy #Web3.0
620
2.10k
2.96k
zettelkasten.de/introduction/
Apr 14, 2023
15 Highlights
thebigidea.nz/about-the-big-idea
Apr 13, 2023
2 Highlights
obsidian.md/
Apr 13, 2023
9 Highlights
www.youtube.com/watch?v=wFZHuWLA09M
Apr 13, 2023
10 Highlights
nesslabs.com/neuromyths?mc_cid=776c5f394a&mc_eid=[755f66218f]
Apr 11, 2023
1 Highlights
medium.com/better-marketing/roam-research-is-the-best-writing-investment-ive-ever-made-a62fc2ffe752
Apr 11, 2023
5 Highlights
www.sciencedaily.com/releases/1998/11/981126102802.htm
Apr 10, 2023
2 Highlights
openai.com/research/gpt-4
Apr 6, 2023
1 Highlights
www.britannica.com/money/how-to-raise-your-credit-score
Apr 4, 2023
1 Highlights
www.quora.com/What-are-some-good-books-by-Carlos-Castaneda
Apr 4, 2023
2 Highlights
www.thenile.co.nz/books/douglas-r-hofstadter/godel-escher-bach-an-eternal-golden-braid/9780465026562?gclid=Cj0KCQjw8qmhBhClARIsANAtbodAPiRMzIwt3M8A_1j8RX3cn9VSvHQZ0IqYu6ZEGDNR7BZUyaPxN78aAkYAEALw_wcB
Apr 3, 2023
1 Highlights
interactives.stuff.co.nz/2017/06/the-americans/part2/
Mar 31, 2023
1 Highlights
www.nzedge.com/news/brilliance-katherine-mansfield/
Mar 31, 2023
1 Highlights
www.nzedge.com/news/silicon-valley-whizz-kids-pitch-new-zealand/
Mar 31, 2023
2 Highlights
namaste.org/about-us
Mar 31, 2023
3 Highlights
en.wikipedia.org/wiki/Lex_Fridman
Mar 30, 2023
3 Highlights
www.holo.mg/shop/n-o-r-m-a-l-s-0-0-1-0-0-3/
Mar 30, 2023
3 Highlights
www.newsroom.co.nz/beca-a-100-year-old-kiwi-grown-multinational
Mar 27, 2023
8 Highlights
clockify.me/timeboxing
Mar 3, 2023
4 Highlights
en.wikipedia.org/wiki/Michael_Faraday
Mar 3, 2023
1 Highlights
www.deepmind.com/blog/building-interactive-agents-in-video-game-worlds
Mar 1, 2023
4 Highlights
www.forbes.com/sites/alexkonrad/2023/02/03/exclusive-openai-sam-altman-chatgpt-agi-google-search/?sh=540838636a63
Mar 1, 2023
4 Highlights
europeanbitcoiners.com/bitcoin-nikola-teslas/
Feb 17, 2023
2 Highlights
allthatsinteresting.com/nikola-tesla-3-6-9
Feb 17, 2023
1 Highlights
bigthink.com/health/neurogenesis-in-adults/
Feb 9, 2023
5 Highlights
pubmed.ncbi.nlm.nih.gov/10195220/
Feb 9, 2023
1 Highlights
www.karger.com/Article/FullText/350946
Feb 9, 2023
1 Highlights
www.verywellmind.com/what-is-the-peripheral-nervous-system-2795465
Feb 9, 2023
13 Highlights
a16z.com/2023/01/19/who-owns-the-generative-ai-platform/
Feb 9, 2023
2 Highlights
qbi.uq.edu.au/brain/nature-discovery/can-we-regrow-our-brains
Feb 9, 2023
3 Highlights
qbi.uq.edu.au/article/2023/01/new-technology-may-help-inform-brain-stimulation
Feb 8, 2023
4 Highlights
qbi.uq.edu.au/article/2018/01/digging-deep-distinctly-different-dna
Feb 8, 2023
2 Highlights
www.livescience.com/why-does-the-brain-use-so-much-energy
Feb 8, 2023
5 Highlights
hbr.org/2023/01/the-permissionless-corporation
Feb 8, 2023
5 Highlights
www.newscientist.com/article/2358426-google-bard-advert-shows-new-ai-search-tool-making-a-factual-error/
Feb 8, 2023
1 Highlights
www.taxconsulting.co.za/news-under-which-circumstances-are-you-allowed-to-withdraw-your-retirement-annuity/
Feb 7, 2023
1 Highlights
www.additudemag.com/autism-in-women-adhd-signs-symptoms-treatment/?utm_source=eletter&utm_medium=email&utm_campaign=adult_february_2023&utm_content=020723&goal=0_d9446392d6-61f3b87dce-303993329
Feb 7, 2023
1 Highlights
www.u-school.org/offerings/ulab-1x-2022
Feb 7, 2023
1 Highlights
nanoglobals.com/glossary/henri-fayol-management-theory/
Feb 7, 2023
3 Highlights
seriousplaypro.com/2018/05/28/lego-serious-play-for-theory-u-learn-to-lead-from-the-future/
Feb 7, 2023
11 Highlights
While imitation learning leads to interesting interactions, it treats each moment of interaction as equally important. To learn efficient, goal-directed behaviour, an agent needs to pursue an objective and master particular movements and decisions at key moments. For example, imitation-based agents don’t reliably take shortcuts or perform tasks with greater dexterity than an average human player.
To train a reward model, we asked humans to judge if they observed events indicating conspicuous progress toward the current instructed goal or conspicuous errors or mistakes. We then drew a correspondence between these positive and negative events and positive and negative preferences. Since they take place across time, we call these judgements “inter-temporal.” We trained a neural network to predict these human preferences and obtained as a result a reward (or utility / scoring) model reflecting human feedback.
Once we trained the reward model using human preferences, we used it to optimise agents. We placed our agents into the simulator and directed them to answer questions and follow instructions. As they acted and spoke in the environment, our trained reward model scored their behaviour, and we used an RL algorithm to optimise agent performance.
We asked people to evaluate our agents in online real-time interactions. Humans gave instructions or questions for 5 min and judged the agents’ success. By using RL our agents obtain a higher success rate compared to imitation-learning alone, achieving 92%the performance of humans in similar conditions.