--- title: '‘LaMDA’ directory' description: "Bibliography for directory ai/nn/transformer/gpt/lamda, most recent first: 1 related tag, 30 annotations, & 7 links ()." thumbnail: /doc/ai/nn/transformer/gpt/lamda/2022-wang-figure5b-selfconsistencycompletionsimprovewithmodelscale.png thumbnail-text: '' thumbnail-css: "outline" created: 2020-01-27 modified: 2024-11-11 status: in progress previous: /doc/ai/nn/transformer/gpt/jukebox/index next: /doc/ai/nn/transformer/gpt/nonfiction/index confidence: log importance: 0 css-extension: dropcaps-not index: True backlink: False ... ::: {#manual-annotation .abstract-small .abstract-tag-directory} [\[page summary\]](/doc/ai/nn/transformer/gpt/lamda/abstract "Transclude link for doc/ai/nn/transformer/gpt/lamda/ tag-abstract page."){#gwern-doc-ai-nn-transformer-gpt-lamda-abstract .link-annotated-partial .include-content-core .include-strict .link-page} ::: # See Also ::: {#see-alsos .directory-indexes .columns} - [Parent ('*`GPT`{=html}*' tag)](/doc/ai/nn/transformer/gpt/index "Link to parent directory 'doc/ai/nn/transformer/gpt/' (ascending)"){#_oXgNdn-X .link-annotated .link-tag .directory-indexes-upwards rel="tag"} - [*`PaLM`{=html}*](/doc/ai/nn/transformer/gpt/palm/index "‘PaLM’ directory"){#_uMX5LVP3 .link-annotated .link-tag .directory-indexes-sideways rel="tag"} ::: # Links {.display-pop-not} ## `“The Death and Life of Prediction Markets at Google: Over the past Two Decades, Google Has Hosted Two Different Internal Platforms for Predictions. Why Did the First One Fail—And Will the Other Endure?”, Schwarz 2024`{=html} {#schwarz-2024-section} **[`The Death and Life of Prediction Markets at Google: Over the past two decades, Google has hosted two different internal platforms for predictions. Why did the first one fail—and will the other endure?`{=html}](https://asteriskmag.com/issues/08/the-death-and-life-of-prediction-markets-at-google "'The Death and Life of Prediction Markets at Google: Over the past two decades, Google has hosted two different internal platforms for predictions. Why did the first one fail—and will the other endure?', Schwarz 2024"){.link-annotated-partial .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“LLMs Achieve Adult Human Performance on Higher-Order Theory of Mind Tasks”, Street et al 2024`{=html} {#street-et-al-2024-section} **[`LLMs achieve adult human performance on higher-order theory of mind tasks`{=html}](https://arxiv.org/abs/2405.18870#google "'LLMs achieve adult human performance on higher-order theory of mind tasks', Street et al 2024"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Google Is Asking Employees to Test Potential ChatGPT Competitors, including a Chatbot Called ‘Apprentice Bard’”, Elias 2023`{=html} {#elias-2023-2-section} **[`Google is asking employees to test potential ChatGPT competitors, including a chatbot called ‘Apprentice Bard’`{=html}](https://www.cnbc.com/2023/01/31/google-testing-chatgpt-like-chatbot-apprentice-bard-with-employees.html "'Google is asking employees to test potential ChatGPT competitors, including a chatbot called ‘Apprentice Bard’', Elias 2023"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Creative Writing With Wordcraft, an AI-Powered Writing Assistant: Perspectives from Professional Writers”, Ippolito et al 2022`{=html} {#ippolito-et-al-2022-section} **[`Creative Writing with Wordcraft, an AI-Powered Writing Assistant: Perspectives from Professional Writers`{=html}](https://arxiv.org/abs/2211.05030#google "'Creative Writing with Wordcraft, an AI-Powered Writing Assistant: Perspectives from Professional Writers', Ippolito et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Language Model Cascades”, Dohan et al 2022`{=html} {#dohan-et-al-2022-section} **[`Language Model Cascades`{=html}](https://arxiv.org/abs/2207.10342#google "'Language Model Cascades', Dohan et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Exploring Length Generalization in Large Language Models”, Anil et al 2022`{=html} {#anil-et-al-2022-section} **[`Exploring Length Generalization in Large Language Models`{=html}](https://arxiv.org/abs/2207.04901#google "'Exploring Length Generalization in Large Language Models', Anil et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Least-To-Most Prompting Enables Complex Reasoning in Large Language Models”, Zhou et al 2022`{=html} {#zhou-et-al-2022-1-section} **[`Least-to-Most Prompting Enables Complex Reasoning in Large Language Models`{=html}](https://arxiv.org/abs/2205.10625#google "'Least-to-Most Prompting Enables Complex Reasoning in Large Language Models', Zhou et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Google Is Beta Testing Its AI Future: After Mistakes and Challenges, the Company Is Moving a Little Slower With AI Language Models”, Vincent 2022`{=html} {#vincent-2022-section} **[`Google is beta testing its AI future: After mistakes and challenges, the company is moving a little slower with AI language models`{=html}](https://www.theverge.com/2022/5/11/23065072/google-ai-app-test-kitchen-future-io-2022 "'Google is beta testing its AI future: After mistakes and challenges, the company is moving a little slower with AI language models', Vincent 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“PaLM: Scaling Language Modeling With Pathways”, Chowdhery et al 2022`{=html} {#chowdhery-et-al-2022-section} **[`PaLM: Scaling Language Modeling with Pathways`{=html}](https://arxiv.org/abs/2204.02311#google "'PaLM: Scaling Language Modeling with Pathways', Chowdhery et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Self-Consistency Improves Chain-Of-Thought Reasoning in Language Models”, Wang et al 2022`{=html} {#wang-et-al-2022-20-section} **[`Self-Consistency Improves Chain-of-Thought Reasoning in Language Models`{=html}](https://arxiv.org/abs/2203.11171#google "'Self-Consistency Improves Chain-of-Thought Reasoning in Language Models', Wang et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“PromptChainer: Chaining Large Language Model Prompts through Visual Programming”, Wu et al 2022`{=html} {#wu-et-al-2022-09-section} **[`PromptChainer: Chaining Large Language Model Prompts through Visual Programming`{=html}](https://arxiv.org/abs/2203.06566#google "'PromptChainer: Chaining Large Language Model Prompts through Visual Programming', Wu et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Using Natural Language Prompts for Machine Translation”, Garcia & Firat 2022`{=html} {#garcia-firat-2022-section} **[`Using natural language prompts for machine translation`{=html}](https://arxiv.org/abs/2202.11822#google "'Using natural language prompts for machine translation', Garcia & Firat 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models”, Wei et al 2022`{=html} {#wei-et-al-2022-4-section} **[`Chain-of-Thought Prompting Elicits Reasoning in Large Language Models`{=html}](https://arxiv.org/abs/2201.11903#google "'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models', Wei et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“LaMDA: Language Models for Dialog Applications”, Thoppilan et al 2022`{=html} {#thoppilan-et-al-2022-section} **[`LaMDA: Language Models for Dialog Applications`{=html}](https://arxiv.org/abs/2201.08239#google "'LaMDA: Language Models for Dialog Applications', Thoppilan et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Google LaMDA LLM”, Gwern 2022`{=html} {#gwern-doc-ai-nn-transformer-gpt-lamda-abstract-section} **[`Google LaMDA LLM`{=html}](/doc/ai/nn/transformer/gpt/lamda/abstract "'Google LaMDA LLM', Gwern 2022"){.link-annotated-partial .id-not .include-annotation}** ## `“SynthBio: A Case Study in Faster Curation of Text Datasets”, Yuan et al 2022`{=html} {#yuan-et-al-2022-1-section} **[`SynthBio: A Case Study in Faster Curation of Text Datasets`{=html}](https://openreview.net/forum?id=Fkpr2RYDvI1#google "'SynthBio: A Case Study in Faster Curation of Text Datasets', Yuan et al 2022"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Discovering the Syntax and Strategies of Natural Language Programming With Generative Language Models”, Jiang et al 2022`{=html} {#jiang-et-al-2022-7-section} **[`Discovering the Syntax and Strategies of Natural Language Programming with Generative Language Models`{=html}](/doc/ai/nn/transformer/gpt/lamda/2022-jiang.pdf "'Discovering the Syntax and Strategies of Natural Language Programming with Generative Language Models', Jiang et al 2022"){.link-annotated .id-not .include-annotation link-icon="pdf" link-icon-type="svg" link-icon-color="#f40f02"}** ## `“GLaM: Efficient Scaling of Language Models With Mixture-Of-Experts”, Du et al 2021`{=html} {#du-et-al-2021-1-section} **[`GLaM: Efficient Scaling of Language Models with Mixture-of-Experts`{=html}](https://arxiv.org/abs/2112.06905#google "'GLaM: Efficient Scaling of Language Models with Mixture-of-Experts', Du et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Show Your Work: Scratchpads for Intermediate Computation With Language Models”, Nye et al 2021`{=html} {#nye-et-al-2021-section} **[`Show Your Work: Scratchpads for Intermediate Computation with Language Models`{=html}](https://arxiv.org/abs/2112.00114#google "'Show Your Work: Scratchpads for Intermediate Computation with Language Models', Nye et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts”, Wu et al 2021`{=html} {#wu-et-al-2021-07-section} **[`AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts`{=html}](https://arxiv.org/abs/2110.01691#google "'AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts', Wu et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“A Recipe For Arbitrary Text Style Transfer With Large Language Models”, Reif et al 2021`{=html} {#reif-et-al-2021-section} **[`A Recipe For Arbitrary Text Style Transfer with Large Language Models`{=html}](https://arxiv.org/abs/2109.03910#google "'A Recipe For Arbitrary Text Style Transfer with Large Language Models', Reif et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“GenLine and GenForm: Two Tools for Interacting With Generative Language Models in a Code Editor”, Jiang et al 2021b`{=html} {#jiang-et-al-2021b-section} **[`GenLine and GenForm: Two Tools for Interacting with Generative Language Models in a Code Editor`{=html}](/doc/ai/nn/transformer/gpt/lamda/2021-jiang-2.pdf "'GenLine and GenForm: Two Tools for Interacting with Generative Language Models in a Code Editor', Jiang et al 2021b"){.link-annotated .id-not .include-annotation link-icon="pdf" link-icon-type="svg" link-icon-color="#f40f02"}** ## `“FLAN: Finetuned Language Models Are Zero-Shot Learners”, Wei et al 2021`{=html} {#wei-et-al-2021-1-section} **[`FLAN: Finetuned Language Models Are Zero-Shot Learners`{=html}](https://arxiv.org/abs/2109.01652#google "'FLAN: Finetuned Language Models Are Zero-Shot Learners', Wei et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Program Synthesis With Large Language Models”, Austin et al 2021`{=html} {#austin-et-al-2021-1-section} **[`Program Synthesis with Large Language Models`{=html}](https://arxiv.org/abs/2108.07732#google "'Program Synthesis with Large Language Models', Austin et al 2021"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“Towards a Human-Like Open-Domain Chatbot”, Adiwardana et al 2020`{=html} {#adiwardana-et-al-2020-section} **[`Towards a Human-like Open-Domain Chatbot`{=html}](https://arxiv.org/abs/2001.09977#google "'Towards a Human-like Open-Domain Chatbot', Adiwardana et al 2020"){.link-annotated .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“LaMDA: Our Breakthrough Conversation Technology”`{=html} {#_x-GBXFt7-section} **[`LaMDA: our breakthrough conversation technology`{=html}](https://blog.google/technology/ai/lamda/ "LaMDA: our breakthrough conversation technology"){.link-annotated-partial .id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ## `“308 Permanent Redirect”`{=html} {#_0icF18zv-section} **[`308 Permanent Redirect`{=html}](https://character.ai/ "308 Permanent Redirect"){.id-not .include-annotation}** ## `“Do Large Language Models Understand Us?”`{=html} {#_LgjQwtV0-section} **[`Do large language models understand us?`{=html}](https://medium.com/@blaisea/do-large-language-models-understand-us-6f881d6d8e75 "Do large language models understand us?"){.id-not .include-annotation link-icon="𝐌" link-icon-type="text"}** ## `“The Race to Understand the Thrilling, Dangerous World of Language AI”`{=html} {#_PAwMzEzY-section} **[`The race to understand the thrilling, dangerous world of language AI`{=html}](https://www.technologyreview.com/2021/05/20/1025135/ai-large-language-models-bigscience-project/ "The race to understand the thrilling, dangerous world of language AI"){.link-annotated-partial .id-not .include-annotation link-icon="T" link-icon-type="text,sans"}** ## `“Watch Google’s AI LaMDA Program Talk to Itself at Length (Full Conversation)”`{=html} {#_IHBr4sn0-section} **[`Watch Google’s AI LaMDA program talk to itself at length (full conversation)`{=html}](https://www.youtube.com/watch?v=aUSSfo5nCdM#google "Watch Google’s AI LaMDA program talk to itself at length (full conversation)"){.id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ::: aux-links-transclude-file [`https://www.youtube.com/watch?v=aUSSfo5nCdM#google`](https://www.youtube.com/watch?v=aUSSfo5nCdM#google){.link-annotated-not .include-content .width-full} ::: ## Sort By Magic ::: {demo-type="sort-by-magic-preface"} Annotations sorted by machine learning into [inferred \'tags\'](/design#future-tag-features){#gwern-design--future-tag-features .link-annotated-partial}. This provides an alternative way to browse: instead of by *date* order, one can browse in *topic* order. The \'sorted\' list has been automatically clustered into multiple sections & auto-labeled for easier browsing. Beginning with the newest annotation, it uses the embedding of each annotation to attempt to create a list of nearest-neighbor annotations, creating a progression of topics. For more details, see the link. ::: ### `theory-of-mind` {.collapse title="Machine-generated tag name for the following cluster of links."} [\[see previous entry\]](#street-et-al-2024-section){.include .include-even-when-collapsed} [\[see previous entry\]](#yuan-et-al-2022-1-section){.include .include-even-when-collapsed} ### `scaling-models` {.collapse title="Machine-generated tag name for the following cluster of links."} [\[see previous entry\]](#du-et-al-2021-1-section){.include .include-even-when-collapsed} [\[see previous entry\]](#chowdhery-et-al-2022-section){.include .include-even-when-collapsed} ### `reasoning` {.collapse title="Machine-generated tag name for the following cluster of links."} [\[see previous entry\]](#ippolito-et-al-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#wei-et-al-2022-4-section){.include .include-even-when-collapsed} [\[see previous entry\]](#wang-et-al-2022-20-section){.include .include-even-when-collapsed} [\[see previous entry\]](#zhou-et-al-2022-1-section){.include .include-even-when-collapsed} [\[see previous entry\]](#anil-et-al-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#nye-et-al-2021-section){.include .include-even-when-collapsed} [\[see previous entry\]](#austin-et-al-2021-1-section){.include .include-even-when-collapsed} [\[see previous entry\]](#jiang-et-al-2022-7-section){.include .include-even-when-collapsed} [\[see previous entry\]](#jiang-et-al-2021b-section){.include .include-even-when-collapsed} [\[see previous entry\]](#wu-et-al-2022-09-section){.include .include-even-when-collapsed} [\[see previous entry\]](#wu-et-al-2021-07-section){.include .include-even-when-collapsed} [\[see previous entry\]](#dohan-et-al-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#garcia-firat-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#reif-et-al-2021-section){.include .include-even-when-collapsed} [\[see previous entry\]](#wei-et-al-2021-1-section){.include .include-even-when-collapsed} ### `dialogue-ai` {.collapse title="Machine-generated tag name for the following cluster of links."} [\[see previous entry\]](#adiwardana-et-al-2020-section){.include .include-even-when-collapsed} [\[see previous entry\]](#thoppilan-et-al-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#vincent-2022-section){.include .include-even-when-collapsed} [\[see previous entry\]](#elias-2023-2-section){.include .include-even-when-collapsed} # Miscellaneous - **[`/doc/ai/nn/transformer/gpt/lamda/2022-wang-figure5b-selfconsistencycompletionsimprovewithmodelscale.png`{=html}](/doc/ai/nn/transformer/gpt/lamda/2022-wang-figure5b-selfconsistencycompletionsimprovewithmodelscale.png){.link-annotated-partial .id-not .include-annotation link-icon="image" link-icon-type="svg"}** - **[`https://blog.google/technology/ai/bard/-google-ai-search-updates/`{=html}](https://blog.google/technology/ai/bard/-google-ai-search-updates/){.id-not .include-annotation link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"}** ::: aux-links-transclude-file ::: collapse **View External Link**: [`https://blog.google/technology/ai/bard/-google-ai-search-updates/`](https://blog.google/technology/ai/bard/-google-ai-search-updates/){.id-not .link-annotated-not .include-content .include-lazy link-icon="alphabet" link-icon-type="svg" link-icon-color="#4285f4"} ::: ::: - **[`https://news.ycombinator.com/item?id=27198087`{=html}](https://news.ycombinator.com/item?id=27198087){.link-annotated-partial .id-not .include-annotation link-icon="hacker-news" link-icon-type="svg" link-icon-color="#f26522"}** - **[`https://wordcraft-writers-workshop.appspot.com/stories/allison-parrish`{=html}](https://wordcraft-writers-workshop.appspot.com/stories/allison-parrish){.link-annotated-partial .id-not .include-annotation}** - **[`https://wordcraft-writers-workshop.appspot.com/stories/diana-hamilton`{=html}](https://wordcraft-writers-workshop.appspot.com/stories/diana-hamilton){.link-annotated-partial .id-not .include-annotation}** - **[`https://wordcraft-writers-workshop.appspot.com/stories/eugenia-triantafyllou`{=html}](https://wordcraft-writers-workshop.appspot.com/stories/eugenia-triantafyllou){.link-annotated-partial .id-not .include-annotation}** - **[`https://x.com/glenngabe/status/1563241743260471298`{=html}](https://x.com/glenngabe/status/1563241743260471298 "glenngabe 2026"){.link-annotated-partial .id-not .include-annotation link-icon="twitter" link-icon-type="svg" link-icon-color="#1da1f2"}** # Bibliography {#link-bibliography-section} 1. `https://arxiv.org/abs/2405.18870#google`: [`“LLMs Achieve Adult Human Performance on Higher-Order Theory of Mind Tasks”`{=html}](https://arxiv.org/abs/2405.18870#google "'LLMs achieve adult human performance on higher-order theory of mind tasks', Street et al 2024"){#street-et-al-2024 .link-annotated}, [Winnie Street, John Oliver Siy, Geoff Keeling[, Adrien Baranes, Benjamin Barnett, Michael McKibben, Tatenda Kanyere, Alison Lentz, [Blaise Aguera y Arcas](https://en.wikipedia.org/wiki/Blaise_Aguera_y_Arcas "Blaise Aguera y Arcas"){.id-not}, Robin I. M. Dunbar]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2405.18870%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2405.18870#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 2. `https://www.cnbc.com/2023/01/31/google-testing-chatgpt-like-chatbot-apprentice-bard-with-employees.html`: [`“Google Is Asking Employees to Test Potential ChatGPT Competitors, including a Chatbot Called ‘Apprentice Bard’”`{=html}](https://www.cnbc.com/2023/01/31/google-testing-chatgpt-like-chatbot-apprentice-bard-with-employees.html "'Google is asking employees to test potential ChatGPT competitors, including a chatbot called ‘Apprentice Bard’', Elias 2023"){#elias-2023-2 .link-annotated}, [Jennifer Elias]{.author .cite-author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Fwww.cnbc.com%252F2023%252F01%252F31%252Fgoogle-testing-chatgpt-like-chatbot-apprentice-bard-with-employees.html.html "Directory-tag link-bibliography for link https://www.cnbc.com/2023/01/31/google-testing-chatgpt-like-chatbot-apprentice-bard-with-employees.html"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 3. `https://arxiv.org/abs/2211.05030#google`: [`“Creative Writing With Wordcraft, an AI-Powered Writing Assistant: Perspectives from Professional Writers”`{=html}](https://arxiv.org/abs/2211.05030#google "'Creative Writing with Wordcraft, an AI-Powered Writing Assistant: Perspectives from Professional Writers', Ippolito et al 2022"){#ippolito-et-al-2022 .link-annotated}, [[Daphne Ippolito](https://www.daphnei.com/){.id-not}, Ann Yuan, Andy Coenen, Sehmon Burnam]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2211.05030%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2211.05030#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 4. `https://arxiv.org/abs/2205.10625#google`: [`“Least-To-Most Prompting Enables Complex Reasoning in Large Language Models”`{=html}](https://arxiv.org/abs/2205.10625#google "'Least-to-Most Prompting Enables Complex Reasoning in Large Language Models', Zhou et al 2022"){#zhou-et-al-2022-1 .link-annotated}, [[Denny Zhou](https://dennyzhou.github.io/ "Denny Zhou’s Home Page"){.link-annotated-partial .id-not}, Nathanael Schärli, Le Hou[, [Jason Wei](https://www.jasonwei.net/ "Jason Wei"){.id-not}, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, [Quoc V. Le](https://en.wikipedia.org/wiki/Quoc_V._Le "Quoc V. Le"){.id-not}, [Ed Chi](https://en.wikipedia.org/wiki/Ed_Chi "Ed Chi"){.id-not}]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2205.10625%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2205.10625#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 5. `https://www.theverge.com/2022/5/11/23065072/google-ai-app-test-kitchen-future-io-2022`: [`“Google Is Beta Testing Its AI Future: After Mistakes and Challenges, the Company Is Moving a Little Slower With AI Language Models”`{=html}](https://www.theverge.com/2022/5/11/23065072/google-ai-app-test-kitchen-future-io-2022 "'Google is beta testing its AI future: After mistakes and challenges, the company is moving a little slower with AI language models', Vincent 2022"){#vincent-2022 .link-annotated}, [James Vincent]{.author .cite-author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Fwww.theverge.com%252F2022%252F5%252F11%252F23065072%252Fgoogle-ai-app-test-kitchen-future-io-2022.html "Directory-tag link-bibliography for link https://www.theverge.com/2022/5/11/23065072/google-ai-app-test-kitchen-future-io-2022"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 6. `https://arxiv.org/abs/2204.02311#google`: [`“PaLM: Scaling Language Modeling With Pathways”`{=html}](https://arxiv.org/abs/2204.02311#google "'PaLM: Scaling Language Modeling with Pathways', Chowdhery et al 2022"){#chowdhery-et-al-2022 .link-annotated}, [Aakanksha Chowdhery, [Sharan Narang](https://scholar.google.com/citations?user=CWOixywAAAAJ "Sharan Narang"){.link-modified-recently .id-not}, Jacob Devlin[, [Maarten Bosma](https://ma2rten.github.io/ "Maarten Bosma"){.link-annotated-partial .id-not}, Gaurav Mishra, [Adam Roberts](https://scholar.google.com/citations?user=U5UpKq8AAAAJ "Adam Roberts"){.id-not}, [Paul Barham](https://en.wikipedia.org/wiki/Paul_Barham "Paul Barham"){.id-not}, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, [Parker Barnes](https://en.wikipedia.org/wiki/Parker_Barnes "Parker Barnes"){.id-not}, [Yi Tay](https://www.yitay.net/ "Yi Tay"){.link-annotated-partial .id-not}, [Noam Shazeer](https://en.wikipedia.org/wiki/Noam_Shazeer "Noam Shazeer"){.id-not}, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, [James Bradbury](https://x.com/jekbradbury "Bradbury 2026"){.id-not}, [Jacob Austin](https://en.wikipedia.org/wiki/Jacob_Austin "Jacob Austin"){.id-not}, Michael Isard, [Guy Gur-Ari](https://scholar.google.com/citations?user=mx8P4QUAAAAJ "Guy Gur-Ari"){.id-not}, Pengcheng Yin, Toju Duke, Anselm Levskaya, [Sanjay Ghemawat](https://en.wikipedia.org/wiki/Sanjay_Ghemawat "Sanjay Ghemawat"){.id-not}, Sunipa Dev, Henryk Michalewski, Xavier Garcia, [Vedant Misra](http://vedantmisra.com/ "Vedant Misra"){.id-not}, Kevin Robinson, Liam Fedus, [Denny Zhou](https://dennyzhou.github.io/ "Denny Zhou’s Home Page"){.link-annotated-partial .id-not}, [Daphne Ippolito](https://www.daphnei.com/){.id-not}, David Luan, Hyeontaek Lim, [Barret Zoph](https://barretzoph.github.io/ "Barret Zoph"){.link-annotated-partial .id-not}, [Alexander Spiridonov](https://en.wikipedia.org/wiki/Alexander_Spiridonov "Alexander Spiridonov"){.id-not}, Ryan Sepassi, [David Dohan](https://scholar.google.com/citations?user=iZ5cY0AAAAAJ&view_op=list_works&sortby=pubdate "David Dohan"){.id-not}, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, [Aitor Lewkowycz](https://scholar.google.com/citations?user=Yum1ah0AAAAJ "Aitor Lewkowycz"){.id-not}, Erica Moreira, [Rewon Child](https://rewonc.github.io/){.link-annotated-partial .id-not}, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, [Orhan Firat](https://orhanfirat.com/ "Orhan Fırat"){.link-annotated-partial .id-not}, Michele Catasta, [Jason Wei](https://www.jasonwei.net/ "Jason Wei"){.id-not}, Kathy Meier-Hellstern, Douglas Eck, [Jeff Dean](https://en.wikipedia.org/wiki/Jeff_Dean "Jeff Dean"){.link-annotated-partial .id-not}, Slav Petrov, Noah Fiedel]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2204.02311%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2204.02311#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 7. `https://arxiv.org/abs/2203.11171#google`: [`“Self-Consistency Improves Chain-Of-Thought Reasoning in Language Models”`{=html}](https://arxiv.org/abs/2203.11171#google "'Self-Consistency Improves Chain-of-Thought Reasoning in Language Models', Wang et al 2022"){#wang-et-al-2022-20 .link-annotated}, [Xuezhi Wang, [Jason Wei](https://www.jasonwei.net/ "Jason Wei"){.id-not}, Dale Schuurmans[, [Quoc V. Le](https://en.wikipedia.org/wiki/Quoc_V._Le "Quoc V. Le"){.id-not}, [Ed Chi](https://en.wikipedia.org/wiki/Ed_Chi "Ed Chi"){.id-not}, [Denny Zhou](https://dennyzhou.github.io/ "Denny Zhou’s Home Page"){.link-annotated-partial .id-not}]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2203.11171%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2203.11171#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 8. `https://arxiv.org/abs/2202.11822#google`: [`“Using Natural Language Prompts for Machine Translation”`{=html}](https://arxiv.org/abs/2202.11822#google "'Using natural language prompts for machine translation', Garcia & Firat 2022"){#garcia-firat-2022 .link-annotated}, [Xavier Garcia, [Orhan Firat](https://orhanfirat.com/ "Orhan Fırat"){.link-annotated-partial .id-not}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2202.11822%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2202.11822#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 9. `https://arxiv.org/abs/2201.11903#google`: [`“Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models”`{=html}](https://arxiv.org/abs/2201.11903#google "'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models', Wei et al 2022"){#wei-et-al-2022-4 .link-annotated}, [[Jason Wei](https://www.jasonwei.net/ "Jason Wei"){.id-not}, Xuezhi Wang, Dale Schuurmans[, [Maarten Bosma](https://ma2rten.github.io/ "Maarten Bosma"){.link-annotated-partial .id-not}, [Ed Chi](https://en.wikipedia.org/wiki/Ed_Chi "Ed Chi"){.id-not}, [Quoc V. Le](https://en.wikipedia.org/wiki/Quoc_V._Le "Quoc V. Le"){.id-not}, [Denny Zhou](https://dennyzhou.github.io/ "Denny Zhou’s Home Page"){.link-annotated-partial .id-not}]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2201.11903%2523google.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2201.11903#google"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block} 10. `2021-jiang-2.pdf`: [`“GenLine and GenForm: Two Tools for Interacting With Generative Language Models in a Code Editor”`{=html}](/doc/ai/nn/transformer/gpt/lamda/2021-jiang-2.pdf "'GenLine and GenForm: Two Tools for Interacting with Generative Language Models in a Code Editor', Jiang et al 2021b"){#jiang-et-al-2021b .link-annotated}, [Ellen Jiang, Edwin Toh, Alejandra Molina[, Aaron Donsbach, Carrie Cai, Michael Terry]{.collapse}]{.author} [[link-bibliography](/metadata/annotation/link-bibliography/%252Fdoc%252Fai%252Fnn%252Ftransformer%252Fgpt%252Flamda%252F2021-jiang-2.pdf.html "Directory-tag link-bibliography for link /doc/ai/nn/transformer/gpt/lamda/2021-jiang-2.pdf"){.id-not .include-even-when-collapsed}]{.collapse .tag-index-link-bibliography-block}