corpus.blog
41,832 blogs · 5,239,565 posts Claim your blog
Record · corpus.blog/posts/01a0871f-8d82-7305-8315-079b6cc888c6

AI alignment project ideas

bluedot.org · published 12 April 2024

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at bluedot.org Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
60
Words captured
5,178

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.alignmentforum.org/posts/ChDH335ckdvpxXaXX/model-organisms-of-misalignment-the-case-for-a-new-pillar-of-1
alignmentforum.org
https://aisafetyfundamentals.com/blog/ai-risks/
aisafetyfundamentals.com
https://ollama.com/library/llama2-uncensored
ollama.com
https://www.ibm.com/blog/phishing-simulation/
ibm.com
https://hubbardresearch.com/publications/how-to-measure-anything-book/
hubbardresearch.com
https://www.squiggle-language.com/docs
squiggle-language.com
https://www.adept.ai/blog/act-1
adept.ai
https://twitter.com/OpenInterpreter/status/1770821439458840846
twitter.com
https://github.com/Significant-Gravitas/AutoGPT
github.com
https://research.google/blog/screenai-a-visual-language-model-for-ui-and-visually-situated-language-understanding/
research.google
https://epochai.org/blog/will-we-run-out-of-ml-data-evidence-from-projecting-dataset
epochai.org
https://assets.publishing.service.gov.uk/media/650449e86771b90014fdab4c/Full_Non-Confidential_Report_PDFA.pdf
assets.publishing.service.gov.uk
https://python.langchain.com/v0.1/docs/guides/productionization/safety/constitutional_chain/
python.langchain.com
https://www.lesswrong.com/posts/pc8uP4S9rDoNpwJDZ/claude-3-claims-it-s-conscious-doesn-t-want-to-die-or-be
lesswrong.com
How we could stumble into AI catastrophe Read at the source ↗
cold-takes.com
https://www.alignmentforum.org/posts/YWwzccGbcHMJMpT45/ai-safety-via-market-making
alignmentforum.org
https://arxiv.org/pdf/2402.06782.pdf
arxiv.org
https://docs.google.com/document/d/1KOxKFVfrWUtbPyQvWAktUD5tzEKHtTzzWQrpuplNUV4/edit
docs.google.com
https://arxiv.org/pdf/2308.03958.pdf
arxiv.org
https://aisafetyfundamentals.com/blog/scalable-oversight-intro/
aisafetyfundamentals.com
https://cdn.openai.com/papers/weak-to-strong-generalization.pdf
cdn.openai.com
https://github.com/google/BIG-bench
github.com
https://arxiv.org/pdf/2401.12187.pdf
arxiv.org
https://www.alignmentforum.org/posts/LbrPTJ4fmABEdEnLf/200-concrete-open-problems-in-mechanistic-interpretability
alignmentforum.org
https://www.notion.so/7934b3cbcfbf4f249acac8842f887a99?pvs=21
notion.so
https://arena3-chapter1-transformer-interp.streamlit.app/
arena3-chapter1-transformer-interp.streamlit.app
https://devinterp.com/projects
devinterp.com
https://github.com/timaeus-research/devinterp/blob/main/examples/introduction.ipynb
github.com
https://devinterp.com/discord
devinterp.com
https://www.gov.uk/government/publications/emerging-processes-for-frontier-ai-safety/emerging-processes-for-frontier-ai-safety
gov.uk
https://www.lesswrong.com/posts/XvN2QQpKTuEzgkZHY/being-the-pareto-best-in-the-world
lesswrong.com
https://course.aisafetyfundamentals.com/alignment?session=6&scrollTo=exercises
course.aisafetyfundamentals.com
https://metr.org/
metr.org
https://taskdev.metr.org/specification/
taskdev.metr.org
https://taskdev.metr.org/implementation/
taskdev.metr.org
https://taskdev.metr.org/ideas/
taskdev.metr.org
https://github.com/metr/task-standard
github.com
https://c2pa.org/
c2pa.org
https://arxiv.org/pdf/2401.13138.pdf
arxiv.org
https://datatracker.ietf.org/doc/html/rfc8555
datatracker.ietf.org
https://github.com/OpenInterpreter/open-interpreter
github.com
https://far.ai/post/2023-03-safety-vulnerable-world/
far.ai
https://www.youtube.com/watch?v=g4M7stjzR1I
youtube.com
https://www.lesswrong.com/posts/DKtWikjcdApRj3rWr/paper-understanding-and-controlling-a-maze-solving-policy
lesswrong.com
Zoom In: An Introduction to Circuits Read at the source ↗
distill.pub
https://rethinkpriorities.org/publications/us-public-opinion-of-ai-policy-and-risk
rethinkpriorities.org
https://www.ons.gov.uk/businessindustryandtrade/itandinternetindustry/articles/publicawarenessopinionsandexpectationsaboutartificialintelligence/julytooctober2023
ons.gov.uk
https://publicfirst.co.uk/ai/
publicfirst.co.uk
https://www.gov.uk/government/publications/international-survey-of-public-opinion-on-ai-safety
gov.uk
https://www.scientificamerican.com/article/ai-chatbots-can-diagnose-medical-conditions-at-home-how-good-are-they/
scientificamerican.com
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10874112/
ncbi.nlm.nih.gov
https://openreview.net/pdf?id=H7bgz9b9sz
openreview.net
https://en.wikipedia.org/wiki/User_research
en.wikipedia.org
https://www.nist.gov/artificial-intelligence/artificial-intelligence-safety-institute
nist.gov
https://www.gov.uk/government/organisations/ai-safety-institute
gov.uk
https://arxiv.org/abs/2306.09479
arxiv.org
https://www.lesswrong.com/posts/JK9nxcBhQfzEgjjqe/deep-learning-models-might-be-secretly-almost-linear
lesswrong.com
https://atomicshrimp.com/post/2014/01/20/Invention-Dice
atomicshrimp.com
https://commentpicker.com/combination-generator.php
commentpicker.com
https://bluedot.org/contact/
bluedot.org
Elsewhere on bluedot.org (1)