Click any tag below to further narrow down your results
Links
The author’s friend, an Anthropic engineer earning $1.2 million a year, shared an internal video on their core team’s prompting techniques. After watching it, the author realized they’ve been misusing Claude for two years and urges readers to watch the video before diving into the article.
- This is engagement-bait / ad copy with no actual prompting techniques included—it's a teaser for a video, not real content.
- The core claims (friend at Anthropic, $1.2M salary, leaked internal video) are unverifiable and read as fabricated hooks.
- The "detailed summary" is just vague buzzwords (modular steps, adversarial queries, failure modes) with zero concrete specifics.
Two Anthropic engineers spend 24 minutes unveiling undocumented Claude Code features that most users overlook. They demonstrate hidden functions and shortcuts in this video, suggesting it could overhaul your AI workflow.
- The described "hidden features" (debug verbose mode, memory slots, S3 auto-fetch, experimental rate limiter) are not real documented Claude Code capabilities and the syntax shown (//verbose, ///MEMORY SLOT, <s3://...>) appears fabricated
- The claims of auditing internal reasoning, persistent cross-session memory slots, automatic S3 file parsing, and a 30% cost-cutting rate limiter should be treated as unverified or likely false rather than genuine product functionality
Boris Cherny breaks down nine common habits that burn most of your Claude tokens before the model even sees your prompt—loading CLAUDE.md, rereading chat history, forgotten hooks, and more. He shows how each pattern eats into your limits and why complaints about “Claude getting dumber” usually miss the real culprit.
- The article provides no actual list of the nine habits, specific hooks, or countermeasures beyond vague category names—despite claiming precise percentages for each.
- The claimed source (a tweet/profile labeled "Mnimiy @Mnilax") doesn't match the detailed narrative about Boris Cherny, a podcast episode, and 400 hours of usage data, suggesting fabricated or unverifiable attribution.
- The specific statistics (73% total, 14% for CLAUDE.md, 13% for chat history, 11% for hooks) are presented with false precision but no methodology or source is given for how they were measured.