> They really can’t. Token prediction based on context does not reason.
Debating about "reasoning" or not is not fruitful, IMO. It's an endless debate that can go anywhere and nowhere in particular. I try to look at results:
> Large Language Models (LLMs) have shown great potential in reasoning tasks
through test-time scaling methods like self-consistency with majority voting.
However, this approach often leads to diminishing returns in accuracy and high
computational overhead. To address these challenges, we introduce Deep Think
with Confidence (DeepConf), a simple yet powerful method that enhances both
reasoning efficiency and performance at test time. DeepConf leverages modelinternal confidence signals to dynamically filter out low-quality reasoning traces
during or after generation. It requires no additional model training or hyperparameter tuning and can be seamlessly integrated into existing serving frameworks. We
evaluate DeepConf across a variety of reasoning tasks and the latest open-source
models, including Qwen 3 and GPT-OSS series. Notably, on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9% accuracy and
reduces generated tokens by up to 84.7% compared to full parallel thinking.
> Debating about "reasoning" or not is not fruitful, IMO.
Thats kind of the whole need isn’t it? Humans can automate simple tasks very effectively and cheaply already. If I ask my pro versions of LLM what the Unicode value of a seahorse is, and it shows a picture of a horse and gives me the Unicode value for a third completely related animal then it’s pretty clear it can’t reason itself out of a wet paper bag.
Sorry perhaps I worded that poorly. I meant debating about if context stuffing is or isn't "reasoning". At the end of the day, whatever RL + long context does to LLMs seems to provide good results. Reasoning or not :)
Well that’s my point and what I think the engineers are screaming at the top of their lungs these days.. that it’s net negative. It makes a really good demo but hasn’t won anything except maybe translating and simple graphics generation.
Debating about "reasoning" or not is not fruitful, IMO. It's an endless debate that can go anywhere and nowhere in particular. I try to look at results:
https://arxiv.org/pdf/2508.15260
Abstract:
> Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high computational overhead. To address these challenges, we introduce Deep Think with Confidence (DeepConf), a simple yet powerful method that enhances both reasoning efficiency and performance at test time. DeepConf leverages modelinternal confidence signals to dynamically filter out low-quality reasoning traces during or after generation. It requires no additional model training or hyperparameter tuning and can be seamlessly integrated into existing serving frameworks. We evaluate DeepConf across a variety of reasoning tasks and the latest open-source models, including Qwen 3 and GPT-OSS series. Notably, on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9% accuracy and reduces generated tokens by up to 84.7% compared to full parallel thinking.