AI & machine learning2022 · shared on Hacker News

Chain of Thought Prompting Elicits Reasoning in Large Language Models

Explore Chain of Thought Prompting Elicits Reasoning in Large Language Models, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

The conversation around the idea.

Links found in the discussion

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

Canvas is a new way to write and code with ChatGPT

I used o3 to find a remote zeroday in the Linux SMB implementation

DeepMind: A Generalist Agent

Google fires engineer who called its AI sentient

Use Prolog to improve LLM's reasoning

What We Learned from a Year of Building with LLMs

Pathways Language Model (PaLM): Scaling to 540B parameters

Training Language Models to Self-Correct via Reinforcement Learning

Grok-2 Beta Release

Ortega hypothesis

Limitations of DALL-E

Keep your AI claims in check

Learning to think critically about machine learning

Teaching GPT-3 to reverse words

(Unsuccessfully) Fine-tuning GPT to play "Connections"

AI language models are struggling to “get” math

Update on Reflection-70B

Sam Altman's ouster was precipitated by letter to board about AI breakthrough

$335,000 Pay for ‘AI Whisperer’ Jobs Appears in Red-Hot Market

Our Society Is Not Prepared for This Much AI Awesome

Show HN: QwQ-32B APIs – o1 like reasoning at 1% the cost

GPT-4’s secret

Langchain Is Pointless

Am I doing it wrong? (OpenAI test)

Teaching ChatGPT to Speak My Son’s Invented Language

Using "underdrawings" for accurate text and numbers

Bing thinks Mars has 2.5B people based on an AI generated blog wrong answer

LLMs are not greater than the sum of their parts: Stanford researchers

GPT-4 Can't Reason

OpenAI Begins Tackling ChatGPT Data Leak Vulnerability

Understanding Is the New Bottleneck

Chain of Thought Prompting Elicits Reasoning in Large Language Models

ChatGPT scores 80% on SAT reading/writing with collective chain of thought

Oceania Always at War with Eastasia: Generative AI and Knowledge Pollution

We gave GPT-3.5 tools to run, write, commit, and deploy code

Input to GPT Matters a Lot

A guide to prompting AI (for what it is worth)

Andrej Karpathy talks about "Claws"

John Carmack on Fabrice Bellard

The Session You Cannot take with you

Chain of Thought Prompting Elicits Reasoning in Large Language Models

A new chat feature has been released by You Search

GPT-4 performs significantly worse on coding problems not in its training data

One idea leads to another.