Hacker News Reader

I work exclusively with OpenAI cloud models, and most high-quality agent harnesses auto-compact and does pretty well sticking to the plan of action. Papers that research the definition of AGI never include context length, and I myself don't see the logic for it either.

View on HN

“It doesn’t count because I don’t include it”? AGI doesn’t have a clear definition, there’s no consensus here, so that’s just not convincing to me.

I am not going to call something “intelligent” when it can’t sustain a basic conversation.

I don't think there will ever be universal consensus on....anything. But significant research has been published into its definition, by researchers from the main LLM providers, like https://arxiv.org/abs/2510.18212

Also, I would say SOTA LLM models can sustain a longer, more intelligent conversation than most people. Just in context length alone, they can keep track of more context than humans. But they're nowhere near as efficient the human brain, or the attention to quickly connect and find decades worth of memory like us.

Reply on news.ycombinator.com