Subnostr

Emergent properties of Large Language Models (LLM)

The Unpredictable Abilities Emerging From Large AI Models

Large language models like ChatGPT are big enough that they're displing startling, unpredictable behaviors

https://www.quantamagazine.org/the-unpredictable-abilities-emerging-from-large-ai-models-20230316

Discussion: https://news.ycombinator.com/item?id=35195106

Researchers at Google Brain showed how a model prompted to explain itself (a capacity called chain-of-thought reasoning) could correctly solve a math word problem, while the same model without that prompt could not.

...

Reply to this note

Please Login to reply.

Discussion

Victoria Stuart 🇨🇦 🏳️‍⚧️ 2y ago

... (cont'd)

[Google Brain] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

https://arxiv.org/abs/2201.11903

Recent work suggests chain-of-thought prompting changes scaling curves & therefore the point where emergence occurs.

In their paper the Google researchers showed chain-of-thought prompts could elicit emergent behaviors.

Such prompts, which ask the model to explain its reasoning, may help researchers begin to investigate why emergence occurs at all.

...