What is Post-Training?
Training after pretraining, such as tuning on examples and on human preferences, that shapes how a model follows instructions and behaves. At a model lab, product teams negotiate changes to it with researchers; it is not a setting to toggle.
pretrained → tuned · note matches the fork
Post-training mainly shapes a model's…
Write it in your own words in the app.
In real work
The PM made the case for a post-training change the way research expects it: ranked P0 by user impact, with 60 failing transcripts and the rubric they broke.
In the illustration
The bell arrives from the casting pit holding all its metal. On the tuning lathe a cutter shaves the inside wall, strike after strike, until its note matches the fork.
Draft a post-training request in your model for the research team: the behavior to change, five failing transcripts, the rubric they fail, and the user impact that makes it P0.
Try it now
The fastest way to learn a word is to use it. Open this line in the agent you already work in and watch what it does. Change the tool to the one you use.
Go further
01Practice
Make it stick
One term a day, a short quiz, and sentence practice that checks your own words.
02Verify
Prove you know it
Pass the quiz and keep it in a Skills Wallet you can share with anyone who needs proof.
03Career
Find the work that uses it
See which roles lean on this vocabulary, and what they pay in year one.
Learn the next term tomorrow.
Google gives a definition. Prompthaus pairs each term with how it shows up in standups, PRs, prompts, and design reviews. Then it quizzes you until the word sticks. One term a day on iPhone.
