forked from StampyAI/stampy-ui
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
test(stampy.spec): parameterize the test
- Loading branch information
Showing
5 changed files
with
75 additions
and
154 deletions.
There are no files selected for viewing
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
{"items":[{"id":"i-8899afafb469e7a7e3691f2b506fec68b4567eb11d991ce0f21e99ad1527f4ee","type":"row","href":"https://coda.io/apis/v1/docs/fau7sl2hmG/tables/grid-sync-1059-File/rows/i-8899afafb469e7a7e3691f2b506fec68b4567eb11d991ce0f21e99ad1527f4ee","name":"What is AI safety?","index":349,"createdAt":"2023-01-14T14:46:14.123Z","updatedAt":"2023-06-17T00:07:28.126Z","browserLink":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File/_rui-8899afafb469e7a7e3691f2b506fec68b4567eb11d991ce0f21e99ad1527f4ee","values":{"File":"What is AI safety?","Synced":false,"Sync account":{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"stampysaisafetyinfo@gmail.com","url":"https://coda.io/d/_dfau7sl2hmG#_tuGlobal-External-Connections/_rui-1fffa4c7-80ba-4bd0-804e-e432be8d2052","tableId":"Global-External-Connections","rowId":"i-1fffa4c7-80ba-4bd0-804e-e432be8d2052","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tuGlobal-External-Connections"},"Question":"```What is AI safety?```","Link":{"@context":"http://schema.org/","@type":"WebPage","url":"https://docs.google.com/document/d/1zz1c6rRN8Y-CmO0-BGVKI9G6MMg2MUqD247dPcub144/edit?usp=drivesdk"},"Thumbnail":{"@context":"http://schema.org/","@type":"ImageObject","name":"image.jpeg","height":220,"width":170,"url":"https://codahosted.io/docs/fau7sl2hmG/blobs/bl-4_OLuliiY9/28f78d3dc11cb907a9e2d579ff81a56401b61b45973e6b28db154f0ffd7bb7d90a68bf483c431c84f1093036e4d635b78c7a12dd7a7cad4756446dbd4503e4d1af9013f31859a31b8bdae07984e864d1f584394864e13105331e59981ef61d91e3fbbb85","status":"live"},"Doc Created":"2023-01-14T14:48:30.226+01:00","Related Answers DO NOT EDIT":[{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"What is the difference between AI safety, AI alignment, AI control, friendly AI, AI ethics, AI existential safety and AGI safety?","url":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File/_rui-53897773ddbc2889ee036970bb572cffaef2ead71d29cfccecdcac6c51a181a2","tableId":"grid-sync-1059-File","rowId":"i-53897773ddbc2889ee036970bb572cffaef2ead71d29cfccecdcac6c51a181a2","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File"},{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"What approaches are AI alignment organizations working on?","url":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File/_rui-cd5b637d614c18e592dbee9c05adce59dc98163baba9ac36604b736fa76c76ab","tableId":"grid-sync-1059-File","rowId":"i-cd5b637d614c18e592dbee9c05adce59dc98163baba9ac36604b736fa76c76ab","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File"}],"Tags":"","Doc Last Edited":"2023-06-16T22:55:38.462+02:00","Status":{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"Live on site","url":"https://coda.io/d/_dfau7sl2hmG#_tugrid-IWDInbu5n2/_rui-7EfvxV9G0N","tableId":"grid-IWDInbu5n2","rowId":"i-7EfvxV9G0N","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tugrid-IWDInbu5n2"},"Edit Answer":"**[What is AI safety?](https://docs.google.com/document/d/1zz1c6rRN8Y-CmO0-BGVKI9G6MMg2MUqD247dPcub144/edit?usp=drivesdk)**","Alternate Phrasings":"","UI ID DO NOT EDIT":"```8486```","Source Link":"","aisafety.info Link":"**[What is AI safety?](https://aisafety.info/?state=8486_)**","Source":"```Wiki```","All Phrasings":"```What is AI safety?\n```","Initial Order":"","Related IDs":["```6714```","```6178```"],"Rich Text DO NOT EDIT":"```<iframe src=\"https://www.youtube.com/embed/pYXy-A4siMw\" title=\"Intro to AI Safety, Remastered\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>\n\nIn the [coming decades](https://www.cold-takes.com/most-important-century/), AI systems could be invented that outperform humans on most tasks, including strategy, persuasion, economic productivity, scientific research and development, and AI design. We don't know how to [align such systems](https://www.cold-takes.com/why-ai-alignment-could-be-hard-with-modern-deep-learning/) with the intentions of their users, even when those intentions are good. This could lead to catastrophic outcomes.\n\nThe research field of AI safety was founded to prevent such disasters, and enable humanity to use the enormous potential of advanced AI to solve problems and improve the world. There are many kinds of AI risk, but the kind that this website focuses on, because it seems both plausible and extreme in scope, is [existential risk](https://en.wikipedia.org/wiki/Existential_risk_from_artificial_general_intelligence) from misaligned AI systems [disempowering or killing humanity](https://80000hours.org/problem-profiles/artificial-intelligence/#power-seeking-ai).\n\nExamples of work on AI existential safety are:\n\n- [Agent foundations](https://www.alignmentforum.org/posts/FWvzwCDRgcjb9sigb/why-agent-foundations-an-overly-abstract-explanation): Understanding what intelligence and agency are at a fundamental level\n\n- [Prosaic alignment](/?state=89LM): Developing methods like [debate](https://openai.com/research/debate) and [iterated distillation and amplification](/?state=897J) to align more powerful versions of current AI techniques\n\n- [AI policy and governance](https://80000hours.org/articles/ai-policy-guide/): Setting up institutions and mechanisms that cause the major actors to implement good AI safety practices\n\nExamples of work from the broader AI safety field are:\n\n- Getting content recommender systems to not radicalize their users\n\n- Ensuring autonomous cars don’t kill people\n\n- Advocating strict regulations for lethal autonomous weapons\n\nSome kinds of research are useful for addressing both existential risk and smaller-scale bad outcomes:\n\n- [Robustness to distribution shift](https://www.alignmentforum.org/tag/distributional-shifts): making AI systems more able to function reliably outside of the context they were trained in\n\n- [Interpretability](/?state=8241): giving humans insight into the inner workings of AI systems such as neural networks\n\nThis website is a single point of access where people can read summaries and find links to the best information on concepts related to AI existential safety. The goal is to help readers contribute to the effort to ensure that humanity avoids these risks and reaches a wonderful future.\n\n```","Tag Count":0,"Related Answer Count":2,"Rich Text":"```<iframe src=\"https://www.youtube.com/embed/pYXy-A4siMw\" title=\"Intro to AI Safety, Remastered\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>\n\nIn the [coming decades](https://www.cold-takes.com/most-important-century/), AI systems could be invented that outperform humans on most tasks, including strategy, persuasion, economic productivity, scientific research and development, and AI design. We don't know how to [align such systems](https://www.cold-takes.com/why-ai-alignment-could-be-hard-with-modern-deep-learning/) with the intentions of their users, even when those intentions are good. This could lead to catastrophic outcomes.\n\nThe research field of AI safety was founded to prevent such disasters, and enable humanity to use the enormous potential of advanced AI to solve problems and improve the world. There are many kinds of AI risk, but the kind that this website focuses on, because it seems both plausible and extreme in scope, is [existential risk](https://en.wikipedia.org/wiki/Existential_risk_from_artificial_general_intelligence) from misaligned AI systems [disempowering or killing humanity](https://80000hours.org/problem-profiles/artificial-intelligence/#power-seeking-ai).\n\nExamples of work on AI existential safety are:\n\n- [Agent foundations](https://www.alignmentforum.org/posts/FWvzwCDRgcjb9sigb/why-agent-foundations-an-overly-abstract-explanation): Understanding what intelligence and agency are at a fundamental level\n\n- [Prosaic alignment](/?state=89LM): Developing methods like [debate](https://openai.com/research/debate) and [iterated distillation and amplification](/?state=897J) to align more powerful versions of current AI techniques\n\n- [AI policy and governance](https://80000hours.org/articles/ai-policy-guide/): Setting up institutions and mechanisms that cause the major actors to implement good AI safety practices\n\nExamples of work from the broader AI safety field are:\n\n- Getting content recommender systems to not radicalize their users\n\n- Ensuring autonomous cars don’t kill people\n\n- Advocating strict regulations for lethal autonomous weapons\n\nSome kinds of research are useful for addressing both existential risk and smaller-scale bad outcomes:\n\n- [Robustness to distribution shift](https://www.alignmentforum.org/tag/distributional-shifts): making AI systems more able to function reliably outside of the context they were trained in\n\n- [Interpretability](/?state=8241): giving humans insight into the inner workings of AI systems such as neural networks\n\nThis website is a single point of access where people can read summaries and find links to the best information on concepts related to AI existential safety. The goal is to help readers contribute to the effort to ensure that humanity avoids these risks and reaches a wonderful future.\n\n```","Stamp Count":0,"Multi Answer":"","Stamped By":"","Priority":2,"Asker":"```Magdalena```","External Source":"","Last Asked On Discord":"","UI ID":"```8486```","Related Answers":[{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"What is the difference between AI safety, AI alignment, AI control, friendly AI, AI ethics, AI existential safety and AGI safety?","url":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File/_rui-53897773ddbc2889ee036970bb572cffaef2ead71d29cfccecdcac6c51a181a2","tableId":"grid-sync-1059-File","rowId":"i-53897773ddbc2889ee036970bb572cffaef2ead71d29cfccecdcac6c51a181a2","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File"},{"@context":"http://schema.org/","@type":"StructuredValue","additionalType":"row","name":"What approaches are AI alignment organizations working on?","url":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File/_rui-cd5b637d614c18e592dbee9c05adce59dc98163baba9ac36604b736fa76c76ab","tableId":"grid-sync-1059-File","rowId":"i-cd5b637d614c18e592dbee9c05adce59dc98163baba9ac36604b736fa76c76ab","tableUrl":"https://coda.io/d/_dfau7sl2hmG#_tugrid-sync-1059-File"}],"Doc Last Ingested":"2023-06-16T23:16:39.168+02:00","Request Count":"","Number of suggestions on answer doc":0,"Total character count of suggestions on answer doc":0,"Helpful":10,"Number of pending comments":16,"Length":2904}}],"href":"https://coda.io/apis/v1/docs/fau7sl2hmG/tables/grid-sync-1059-File/rows?pageToken=eyJsaW1pdCI6MjAwLCJvZmZzZXQiOjAsIm9wVmVyc2lvbiI6OTgyNDgsInF1ZXJ5IjoiYy0yMDNLd1NDMk5fOlwiODQ4NlwiIiwic2NoZW1hVmVyc2lvbiI6MTcyLCJzb3J0QnkiOiJuYXR1cmFsIiwidXNlQ29sdW1uTmFtZXMiOnRydWUsInZhbHVlRm9ybWF0IjoicmljaCJ9"} |
Oops, something went wrong.