Hacker News Reader

With Claude specifically I've grown confident they have been sneakily experimenting with context compression to save money and doing a very bad job at it. However for this same reason one shot batch usage or one off questions & answers that don't depend on larger context windows don't seem to see this degradation.

View on HN

They added a "How is claude doing?" rating a while back which backs this statement up imo. Tons of A/B tests going on i bet.

Every time I type in cap case or use a 4 letter word with Claude I’ll get hit with the 1 questions survey.

More times than not the answer is 1 (bad, IIRC). Then it’s 2 for fine. I can only ever remember hitting 3 once.

Reply on news.ycombinator.com