News for hackers. Stuff that matters.
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by aftbit on Sunday April 12, 2026 @05:23PM (#47744661)
Huh I've noticed that! Opus hallucinates answers and provides contradictory reasoning to me much more regularly during the past couple of weeks than it did in February.

For example, after a question about a script that used taskset and CUDA_VISIBLE_DEVICES to handle NUMA domains on a parallel GLUE evaluation run:

>Round 2 tasks reuse GPU slots that Round 1 may still be occupying. Cola, SST-2, and QQP are small datasets and will likely finish before MNLI, but QNLI is sizable. If QNLI (GPU 3, slot 3) is still running when Round 2 launches, that's fine — they're on different slots. But more importantly, Round 2 uses slots 5/6/7 (GPUs 7/0/1), while Round 1 uses slots 0/1/2/3/4 (GPUs 4/5/2/3/6). So there's no GPU collision — you're good here actually. Disregard, this is clean.

There are no comments on this comment yet.