So agent harnesses like Claude and Antigravity recently introduced 1M-token context windows, which was great, at first. It turns out that a context window is re-sent on every turn, so a near-full window burns through your usage limit — FAST. Bummer.
So agent harnesses like Claude and Antigravity recently introduced 1M-token context windows, which was great, at first. It turns out that a context window is re-sent on every turn, so a near-full window burns through your usage limit — FAST. Bummer.