Neutral mention · rule
Related check out chain of draft if you haven't. Similar performance with 7% of tokens as chain of thought. https://arxiv.org/abs/2502.18600
Back to the collection
Chain of Draft: Thinking Faster by Writing Less
Silei Xu, Wenhao Xie, Lingxiao Zhao, Pengcheng He
2025 · arXiv
- HN score
- 0
- Mentions
- 3
- Readers
- 3
- Months
- 3
From the abstract
Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning. However, humans typically employ a more efficient strategy: drafting concise intermediate thoughts that capture only essential information. In this work, we propose Chain of Draft (CoD), a novel paradigm inspired by human cognitive processes, where LLMs generate minimalistic yet informative intermediate reasoning outputs while solving tasks. By reducing verbosity and focusing on critical insights, CoD matches or surpasses CoT in accuracy while using as little as only 7.6% of the tokens, significantly reducing cost and latency across various reasoning tasks. Our code and data are available at https://github.com/sileix/chain-of-draft.
Metadata: arXiv. Abstracts retain their original authors’ rights.
In the conversation
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
3 selected excerpts · 3 total mentions
Neutral mention · rule
Very much related to this is "Chain-of-draft" https://arxiv.org/abs/2502.18600 Similar level of results in a fraction of the tokens resulting in similar quality for less cost for longer runs. But also when interacting and needing to read the token responses I can read shorter responses way faster so my own speed is faster.
Neutral mention · rule
This seems near identical to chain of draft, albeit more thorough and they actually did training instead of just promoting https://arxiv.org/abs/2502.18600
Keep following the thread.
More in NeuroscienceMore from the same topics.
2023arXiv
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.
60 mentions14 months
3.5HN score
2020arXiv
Language Models are Few-Shot Learners
Tom B. Brown, Benjamin Mann, Nick Ryder +28
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.
83 mentions35 months
3HN score
2013arXiv
The Ghost in the Quantum Turing Machine
Scott Aaronson
In honor of Alan Turing's hundredth birthday, I unwisely set out some thoughts about one of Turing's obsessions throughout his life, the question of physics and free will.
9 mentions8 months
2.5HN score
2025arXiv
Design Patterns for Securing LLM Agents against Prompt Injections
Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu +11
As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge.
4 mentions4 months
2.5HN score