Thus spoke GPT-3: Interviewing a large-language model on climate finance

Abstract

This paper is an interview with a Large Language Model (LLM), namely GPT-3, on the issues of climate change. The interview should give some insights into the current capabilities of these large models which are deep neural networks with generally more than 100 billion parameters. In particular, it shows how eloquent and convincing the answers of such LLMs can be. However, it should be noted that LLMs can suffer from hallucination and their responses may not be grounded on facts. These deficiencies offer an interesting avenue for future research.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 56 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.