Trackbacks for 2005.14165

Create Your Own Meal Planner Using ChatGPT

[ Towards Data Science - Medium@ towardsdatascience.com/crea... ] trackback posted Thu, 26 Sep 2024 16:58:44 UTC

Designing the relationship between LLMs and user experience

[ Towards Data Science - Medium@ towardsdatascience.com/desi... ] trackback posted Mon, 22 Apr 2024 18:16:07 UTC

Large Language Models, GPT-3: Language Models are Few-Shot Learners

[ Towards Data Science - Medium@ towardsdatascience.com/larg... ] trackback posted Fri, 16 Feb 2024 15:07:39 UTC

The Most Simple Way to Set Up ChatGPT Locally

[ Towards Data Science - Medium@ towardsdatascience.com/the-... ] trackback posted Wed, 17 Jan 2024 17:26:43 UTC

Emergent abilities and grokking: Fundamental, Mirage, or both?

[ Windows On Theory@ windowsontheory.org/2023/12... ] trackback posted Sat, 23 Dec 2023 01:41:22 UTC

Paper Summary: Language Models are Few-Shot Learners

[ ML Paper Summaries@ fanpu.io/summaries/2023-08-... ] trackback posted Thu, 31 Aug 2023 22:48:30 UTC

All You Need to Know about In-Context Learning

[ Towards Data Science - Medium@ towardsdatascience.com/all-... ] trackback posted Tue, 25 Jul 2023 14:28:38 UTC

Metaphors for AI, and why I don't like them

[ Windows On Theory@ windowsontheory.org/2023/06... ] trackback posted Wed, 28 Jun 2023 22:46:34 UTC

Reprompting: Automated Problem-solving Optimization for LLMs

[ Towards Data Science - Medium@ towardsdatascience.com/repr... ] trackback posted Tue, 30 May 2023 13:45:16 UTC

Bob Carpenter says LLMs are intelligent.

[ Statistical Modeling, Causal Inference, and...@ statmodeling.stat.columbia.... ] trackback posted Wed, 24 May 2023 13:38:50 UTC

Towards Stand-Alone Self-Attention in Vision

[ Towards Data Science - Medium@ towardsdatascience.com/towa... ] trackback posted Fri, 28 Apr 2023 05:56:21 UTC

LLM Economics: ChatGPT vs Open-Source

[ Towards Data Science - Medium@ towardsdatascience.com/llm-... ] trackback posted Wed, 26 Apr 2023 15:10:55 UTC

Which GPT-like Engineering Strategies Work on System Logs?

[ Towards Data Science - Medium@ towardsdatascience.com/whic... ] trackback posted Fri, 21 Apr 2023 03:32:49 UTC

Beyond the Turing Test: Two Scenarios for the Future of AGI

[ Towards Data Science - Medium@ towardsdatascience.com/beyo... ] trackback posted Mon, 17 Apr 2023 15:39:52 UTC

Can ChatGPT recommend movies with machine learning

[ Towards Data Science - Medium@ towardsdatascience.com/can-... ] trackback posted Mon, 17 Apr 2023 13:05:17 UTC

Using GPT-3.5-Turbo and GPT-4 to Apply Text-defined Data Quality Checks on Humanitarian Datasets

[ Towards Data Science - Medium@ towardsdatascience.com/usin... ] trackback posted Wed, 29 Mar 2023 13:19:49 UTC

What are the Data-centric AI Concepts behind GPT Models?

[ Towards Data Science - Medium@ towardsdatascience.com/what... ] trackback posted Wed, 29 Mar 2023 04:42:33 UTC

Transformer Neural Network Engineering Techniques on System Logs for Malware Behavior Modeling

[ Towards Data Science - Medium@ towardsdatascience.com/tran... ] trackback posted Tue, 7 Mar 2023 13:15:10 UTC

Guiding Large Language Models towards task-specific inference -- Prompt Design and Soft Prompts

[ Towards Data Science - Medium@ towardsdatascience.com/guid... ] trackback posted Sat, 4 Mar 2023 04:56:56 UTC

Using ChatGPT as a Creative Writing Partner -- Part 3: Picture Books

[ Towards Data Science - Medium@ towardsdatascience.com/usin... ] trackback posted Tue, 7 Feb 2023 13:42:08 UTC

Exploring Token Probabilities as a Means to Filter GPT-3's Answers

[ Towards Data Science - Medium@ towardsdatascience.com/expl... ] trackback posted Thu, 19 Jan 2023 03:41:10 UTC

How to Estimate the Number of Parameters in Transformer models

[ Towards Data Science - Medium@ towardsdatascience.com/how-... ] trackback posted Fri, 13 Jan 2023 15:11:27 UTC

Language Model Scaling Laws and GPT-3

[ Towards Data Science - Medium@ towardsdatascience.com/lang... ] trackback posted Sat, 10 Dec 2022 04:28:04 UTC

Using Transformers for Computer Vision

[ Towards Data Science - Medium@ towardsdatascience.com/usin... ] trackback posted Wed, 5 Oct 2022 04:33:19 UTC

I once trained an AI to rhyme, and it took GPT-J a long time

[ Towards Data Science - Medium@ towardsdatascience.com/i-on... ] trackback posted Tue, 4 Oct 2022 15:42:16 UTC

Talking to machines: prompt engineering & injection

[ Towards Data Science - Medium@ towardsdatascience.com/talk... ] trackback posted Tue, 4 Oct 2022 14:02:03 UTC

Creating a Cover Letter Generator Using Python and GPT-3

[ Towards Data Science - Medium@ towardsdatascience.com/crea... ] trackback posted Mon, 1 Aug 2022 15:35:56 UTC

The Future of Crafting Prompts for Text-to-Image Models

[ Towards Data Science - Medium@ towardsdatascience.com/the-... ] trackback posted Tue, 26 Jul 2022 14:44:33 UTC

Self-supervised Transformer Models -- BERT, GPT3, MUM and PaML

[ Towards Data Science - Medium@ towardsdatascience.com/self... ] trackback posted Wed, 6 Jul 2022 15:30:23 UTC

Sentence Transformer Fine-Tuning (SetFit): Outperforms GPT-3 on few-shot Text-Classification while...

[ Towards Data Science - Medium@ towardsdatascience.com/sent... ] trackback posted Sat, 18 Dec 2021 05:30:06 UTC

What Does It Mean for AI to Understand?

[ Quanta Magazine@ www.quantamagazine.org/what... ] trackback posted Thu, 16 Dec 2021 14:48:04 UTC

Almost no data and no time? Unlocking the true potential of GPT3, a case study.

[ Towards Data Science - Medium@ towardsdatascience.com/almo... ] trackback posted Wed, 13 Oct 2021 14:17:51 UTC

The Computer Scientist Training AI to Think With Analogies

[ Quanta Magazine@ www.quantamagazine.org/mela... ] trackback posted Wed, 14 Jul 2021 16:30:59 UTC

Thirty Fast Text Pre-Processing Code and Benchmarks For Natural Language Processing

[ Towards Data Science - Medium@ towardsdatascience.com/thir... ] trackback posted Mon, 21 Jun 2021 15:45:30 UTC

Application of GPT-3 in Q&A

[ Towards Data Science - Medium@ towardsdatascience.com/appl... ] trackback posted Wed, 16 Jun 2021 13:07:24 UTC

OpenAI PALMS -- Adapting GPT-3 to Society

[ Towards Data Science - Medium@ towardsdatascience.com/open... ] trackback posted Sat, 12 Jun 2021 05:45:25 UTC

GPT-3 Scared You? Meet Wu Dao 2.0: A Monster of 1.75 Trillion Parameters

[ Towards Data Science - Medium@ towardsdatascience.com/gpt-... ] trackback posted Sun, 6 Jun 2021 03:30:26 UTC

4 Things GPT-4 Will Improve From GPT-3

[ Towards Data Science - Medium@ towardsdatascience.com/4-th... ] trackback posted Fri, 28 May 2021 14:35:14 UTC

GPT-3 Use Cases in Job Marketplaces

[ Towards Data Science - Medium@ towardsdatascience.com/gpt-... ] trackback posted Mon, 17 May 2021 15:03:45 UTC

How to Use Transformer-based NLP Models

[ Towards Data Science - Medium@ towardsdatascience.com/how-... ] trackback posted Tue, 11 May 2021 15:00:18 UTC

AI advances, but cat the law keep up?

[ Towards Data Science - Medium@ towardsdatascience.com/ai-a... ] trackback posted Wed, 31 Mar 2021 14:56:47 UTC

What In The Corpus is a Word Embedding?

[ Towards Data Science - Medium@ towardsdatascience.com/what... ] trackback posted Thu, 28 Jan 2021 15:35:45 UTC

From Natural to Artificial language

[ Towards Data Science - Medium@ towardsdatascience.com/from... ] trackback posted Sat, 23 Jan 2021 15:10:33 UTC

Finding the Words to Say: Hidden State Visualizations for Language Models

[ Jay Alammar@ jalammar.github.io/hidden-states/ ] trackback posted Tue, 19 Jan 2021 00:00:00 UTC

Is GPT-3 "reasonable" enough to detect logical fallacies?

[ Towards Data Science - Medium@ towardsdatascience.com/is-g... ] trackback posted Thu, 14 Jan 2021 13:50:03 UTC

Precautions in Using Tech for Public Health Part II: Factoring Climate Change as an Output of...

[ Towards Data Science - Medium@ towardsdatascience.com/prec... ] trackback posted Sun, 27 Dec 2020 16:50:56 UTC

Machine Learning 2020 summary: 84 interesting papers/articles

[ Towards Data Science - Medium@ towardsdatascience.com/mach... ] trackback posted Sat, 19 Dec 2020 15:51:48 UTC

Interfaces for Explaining Transformer Language Models

[ Jay Alammar@ jalammar.github.io/explaini... ] trackback posted Thu, 17 Dec 2020 00:00:00 UTC

The quest for artificial common sense

[ Towards Data Science - Medium@ towardsdatascience.com/the-... ] trackback posted Mon, 14 Dec 2020 14:11:33 UTC

Meet GPT-3. It Has Learned to Code (and Blog and Argue)

[ NYTimes@ www.nytimes.com/2020/11/24/... ] trackback posted Tue, 24 Nov 2020 17:00:00 UTC

GPT-3: The good, the bad and the ugly

[ Towards Data Science - Medium@ towardsdatascience.com/gpt-... ] trackback posted Tue, 29 Sep 2020 14:06:07 UTC

GPT-3, Bloviator: OpenAI's language generator has no idea what it's talking about

[ MIT Technology Review@ www.technologyreview.com/20... ] trackback posted Sat, 22 Aug 2020 16:00:00 UTC

GPT-3: an AI game-changer or an environmental disaster?

[ The Guardian@ www.theguardian.com/comment... ] trackback posted Sat, 1 Aug 2020 15:00:00 UTC

How Do You Know a Human Wrote This?

[ NYTimes@ www.nytimes.com/2020/07/29/... ] trackback posted Wed, 29 Jul 2020 09:00:00 UTC

GPT-3 101: a brief introduction

[ Towards Data Science - Medium@ towardsdatascience.com/gpt-... ] trackback posted Sat, 25 Jul 2020 13:38:15 UTC

Choose Your Quarantine House

[ AI weirdness@ aiweirdness.com/post/624445... ] trackback posted Thu, 23 Jul 2020 16:00:00 UTC

OpenAI's new language generator GPT-3 is shockingly good -- and completely mindless

[ Technology Review@ www.technologyreview.com/20... ] trackback posted Mon, 20 Jul 2020 16:00:00 UTC

OpenAI's latest AI text generator GPT-3 amazes early adopters

[ Silicon Angle@ siliconangle.com/2020/07/19... ] trackback posted Mon, 20 Jul 2020 03:28:00 UTC

OpenAI's GPT-3 may be the biggest thing since bitcoin

[ Manuel Araoz@ maraoz.com/2020/07/18/openai-gpt3/ ] trackback posted Sat, 18 Jul 2020 16:00:00 UTC

Facts about whales

[ AI weirdness@ aiweirdness.com/post/623543... ] trackback posted Wed, 15 Jul 2020 16:00:00 UTC

This is mind blowing.

[ sharifshameem@ twitter.com/sharifshameem/s... ] trackback posted Mon, 13 Jul 2020 14:01:00 UTC

GPT-3: An AI that's eerily good at writing almost anything

[ Arram Sabeti@ arr.am/2020/07/09/gpt-3-an-... ] trackback posted Thu, 9 Jul 2020 16:00:00 UTC

OpenAI Presents GPT-3, a 175 Billion Parameters Language Model

[ Nvidia@ news.developer.nvidia.com/o... ] trackback posted Tue, 7 Jul 2020 16:00:00 UTC

Giving GPT-3 a Turing Test

[ Kevin Lacker's blog@ lacker.io/ai/2020/07/06/giv... ] trackback posted Mon, 6 Jul 2020 16:00:00 UTC

Creating Fake News with OpenAI's Language Models

[ Towards Data Science - Medium@ towardsdatascience.com/crea... ] trackback posted Mon, 22 Jun 2020 15:31:48 UTC

GPT-3 Is Amazing -- And Overhyped

[ Forbes@ www.forbes.com/sites/robtoe... ] trackback posted Fri, 19 Jun 2020 22:56:00 UTC

GPT-3 Creative Fiction

[ Gwern@ www.gwern.net/GPT-3 ] trackback posted Fri, 19 Jun 2020 16:00:00 UTC

Generative Models of Language and Societal Shortcomings

[ Towards Data Science - Medium@ towardsdatascience.com/gene... ] trackback posted Sun, 14 Jun 2020 15:43:15 UTC

Elon Musk-backed OpenAI to release text tool it called dangerous

[ The Guardian@ www.theguardian.com/technol... ] trackback posted Fri, 12 Jun 2020 16:00:00 UTC

OpenAI API

[ OpenAI@ openai.com/blog/openai-api/ ] trackback posted Thu, 11 Jun 2020 16:00:00 UTC

GPT-3: Language Models are Few-Shot Learners

[ Intento@ blog.inten.to/gpt-3-languag... ] trackback posted Tue, 2 Jun 2020 16:00:00 UTC

GPT-3: Language Models are Few-Shot Learners

[ GitHub@ github.com/openai/gpt-3 ] trackback posted Mon, 1 Jun 2020 16:00:00 UTC

GPT-3: The New Mighty Language Model from OpenAI

[ Towards Data Science - Medium@ towardsdatascience.com/gpt-... ] trackback posted Sun, 31 May 2020 15:20:24 UTC

GPT-3: a disappointing paper

[ LessWrong@ www.lesswrong.com/posts/ZHr... ] trackback posted Fri, 29 May 2020 16:00:00 UTC