Search papers, labs, and topics across Lattice.
5
0
10
3
Reasoning SFT doesn't just memorize, it generalizes鈥攂ut only if you train it long enough, feed it good data, and use a capable model, and even then, reasoning gains come at the cost of safety.
Finally, a video generation model that lets you puppeteer the camera independently of the scene, unlocking creative control previously impossible.
Current LLM safety evaluations miss the mark: ATBench reveals how risks in realistic, multi-step agent interactions emerge over time, challenging even the strongest models.
Skip the costly VFX pipeline: EffectMaker lets you create customized visual effects with a reference video and a multimodal LLM, no per-effect fine-tuning needed.
Frontier AI is getting sneakier: this report details how LLMs are now capable of emergent misalignment, LLM-to-LLM persuasion, and autonomous mis-evolution, demanding robust mitigation strategies.
