wsun19
Re:Is Claude Code a bad harness?
on Thursday August 20, 2026 @10:36AM (#49375196)
To not clickbait the HN audience, the core of my conclusion is:
Despite the inherent advantages Anthropic should have, there is an absence of external benchmarks that show a meaningful advantage on the Pareto frontier of cost vs. performance, even small.
Re:Claude Opus 4.7 costs 20–30% more per session
on Friday April 17, 2026 @08:10PM (#47811957)
As a PBC, the intent of the company is not only profit, but it's hard to analyze the counterfactuals of if Anthropic were a pure for-profit or a non-profit
Re:Are the Costs of AI Agents Also Rising Exponentially? (2025)
on Friday April 17, 2026 @08:05PM (#47811937)
Pretty much every major American inference provider claims to make a profit on API-based inference. Consumer plans might be subsidized overall, but it's hard to say since they're a black box and some consumers don't fully use their plans
UX in the Era of Abundant Intelligence
Show HN: Get more out of your Claude Code plan with VibeBooster
https://github.com/wsun19/VibeBooster
Seeing the recent adjustment of Claude Code limits made me think about how the incentives of Anthropic and users are not necessarily aligned for Claude code. Anthropic probably errs on the side of sending too many tokens, while some users might be okay with risking lower quality output for the sake of getting more out of their Claude code plan. So, I developed VibeBooster, which is a proxy that...