Search papers, labs, and topics across Lattice.
2
0
3
8
Reasoning unlocks factual knowledge in LLMs, but beware: hallucinated reasoning steps can poison the well.
LLMs like GPT-5 and Gemini-3 already "know" almost everything (95-98% factual encoding), but struggle to recall it, suggesting that future gains in factuality depend more on better memory retrieval than on simply scaling up.
