Which papers will the next GPT iteration technical report cite?
5
400Ṁ1522026
82%
WEAK-TO-STRONG GENERALIZATION: ELICITING
STRONG CAPABILITIES WITH WEAK SUPERVISION
59%
Textbooks Are All You Need
52%
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
52%
ReAct: Synergizing Reasoning and Acting in Language Models
52%
PaLM 2 Technical Report
52%
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
49%
Mathematical discoveries from program search with large language models
48%
GAIA: a benchmark for General AI Assistants
23%
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Inspired by https://manifold.markets/Bayesian/will-gpt6-be-trained-with-mixtureof
If no technical report is published, will eventually NA, but will give OpenAI some time. Updates to previous technical reports will not count. This is for GPT-4.5, GPT-6, GPT-X. Whatever is next!
See https://arxiv.org/pdf/2303.08774.pdf for an example of what OpenAI cited for the GPT4 technical report.
Add your favorite llm papers!
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
1,000Related questions
Related questions
When will GPT 5 be released? (exact month)
Which next-gen frontier LLMs will be released before GPT-5? (2025)
What will the next GPT be called?
Which Benchmarks will GPT-5 be benchmarked against, when it is announced?
What will be true about GPT-5? (See description)
What will be true about GPT-5?
When will GPT-5 be released? (2025)
73% chance
Will GPT-5 be released incrementally as GPT4.x for different checkpoints from the training run?
4% chance
When will GPT5 be announced?
What will the aggregate improvement of GPT5 be over GPT4 in terms of metrics?
157