$ ls alignment/reviews/ # the step-back reads
Alignment & Post-training in review
One review per week (and month): what shipped, what broke, what to act on.
Oct 5–11, 2026 weekly 8 stories
verl adds TPU SFT via TorchTitan and ETP checkpoint conversion
Both arrive behind the same push that moved the profiler and attention padding paths off CUDA-only assumptions.
Sep 28–Oct 4, 2026 weekly [act] 2 stories
verl adds score centering to bypass-mode REINFORCE
The RFC #8009 implementation lands on the REINFORCE loss path, and verl flags it as breaking for existing training configs.
Keep up with Alignment & Post-training in about 3 minutes: what actually shipped — the commits, pull requests, releases, and security advisories that matter.
fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.
Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.