Critique of Anthropic's verbosity: paying tokens to generate text and then paying again to remove it
0xkeeny · x · 2026-08-22
User critiques Anthropic's /eli5 skill as counterproductive, noting that users pay tokens to generate verbose output and then pay again to summarize it. The comment suggests this is a "refund request with extra steps" rather than a feature, arguing that fixing the default verbosity would eliminate the need for such workarounds.
Related event: Anthropic's internal /eli5 trick goes public as a Claude community plugin(7 posts)→
More from Fun
- ML author Burkov jokes: postal-mail submissions as bullet-proof anti AI-slop fix — francoisfleuret · 2026-10-16
- littmath's poetic AI-automation quip: it'll smell the flower for you — littmath · 2026-10-16
- Surreal AI image turns Dwayne Johnson's torso into a giant rock — OVolosin82152 · 2026-10-16
- Musk amplifies Grok Imagine dance video demo tackling generative AI's hardest motion — elonmusk · 2026-10-16
- Developer Shares That Her 57-Year-Old Chinese Dad Started Using Muse — KlausCodes · 2026-10-16
- UCL Put a Satisfaction Survey Next to Jeremy Bentham's Auto-Icon — gleech · 2026-10-16