18 August 2026

AI models can now learn and adapt while being used

• Test-time training lets models update their internal settings during conversations instead of only before deployment, making them more flexible.
• Models using this approach need less computer memory because they maintain a fixed set of weights rather than storing growing amounts of conversation data.
• The technique trades off between handling very long conversations with personalization against the simpler approach most people use today.

How it was covered

TLDR AITLDR editorial team

Test-time training enables AI models to update their weights during use, reducing memory needs through a fixed-size weight set instead of a growing KV-cache. The trade-off lies between efficient handling of long contexts for personalized services versus broader accessibility of standard models.