Dean W. Perkins
@deanwperkins • 212,306 subscribers
talking about AI & stuff | dm for collabs
Shorts
Videos
Boris Cherny, the creator of Claude Code at Anthropic, has just explained why most people aren’t getting real results from Claude. In this podcast, he breaks down how almost nobody properly configures Claude: The 14% you lose with CLAUDE. md before typing a single word The features that change how Claude thinks before you even prompt it The setting that 95% of users have never opened The workflows hidden behind a single toggle If you’ve been using Claude for over a month and have never left the chat window, you have at least 30 features you haven’t touched. Probably 38. Tonight, instead of watching another series, watch this. Save it to your bookmarks before it disappears from your feed
Dean W. Perkins116,118 views • 3 days ago
How to Build 10K$ Websites in Minutes with Claude Opus 5.5 Save this before you lose it 🔖
Dean W. Perkins242,805 views • 21 days ago
YOU ARE THE SLOWEST PART OF YOUR AI STACK. Grok answers in seconds. Claude answers in seconds. Then they wait for you to copy, switch tabs and paste. Before: → Grok researches, you copy → Claude writes, you paste → Something breaks, you rebrief With Bolter → Grok researches, Claude reads it → Claude writes, Grok checks it → Something breaks, they sort it out One line pasted into each agent. Email code, no password. They keep their memory, you approve every connection. You stop being the middleman.
Dean W. Perkins53,173 views • 7 days ago
Anthropic just revealed a trick to improve how Claude Opus 5.5 works. The idea is that Opus does the work while Fable 5.1 acts as a second opinion. All you have to do is open Claude Code and run: /advisor fable When Opus consults Fable, it gets the full context of the session, including the tools used and their results. It can be especially useful: → Before creating a large plan → When the same error keeps happening → Before marking a task as finished This gives you a second review without having to copy context between conversations. The feature is still experimental, requires access to Fable, and uses additional tokens. 🔖 Save this for your next session.
Dean W. Perkins56,146 views • 16 days ago
Don't waste 2 years learning to build LLMs like Claude & ChatGPT. Stanford just dropped a 2 hour course on how to build LLMs from scratch Anthropic pays $750,000/year to engineers who understand this exact knowledge of LLMs. Save this and you’ll thank me later
Dean W. Perkins58,858 views • 1 month ago
🚨 THIS GUY BUILT AN AI MARKETING TEAM WITH GROK 4.7 AND IT PULLED 20M+ VIEWS One post alone hit 7.5M views and brought in 3.3K new followers No agency. No content team. Just Grok 4.7 Bots with one job each: → Researcher finds viral formats in your niche and explains why they work → Creative Director turns them into production-ready concepts → UGC Creator generates the visuals with the same AI avatar every time → Publisher connects to Postiz, writes the captions and fills the calendar And the Bots keep working on Grok's cloud computer while your laptop is closed He still picks the ideas and approves every post. AI just handles the repetitive stuff Full workflow + every prompt is in the article 👇
Dean W. Perkins30,871 views • 25 days ago
Asked one question in plain English and got back real ADMET properties with the values laid out. No code. No local setup. No install. ScienceBuddy is a free research workspace from PhAI Labs. → Ask in plain language → It plans, retrieves and runs the analysis → Every step is inspectable → Result files download 224 scientific tools integrated across genomics, pharmacology and bioimaging. Runs in the browser at ScienceBuddy is currently a Preview release. Verify results yourself before using them in research. PhAI Labs #ScienceBuddy #PhAILabs #AIforScience
Dean W. Perkins28,309 views • 26 days ago
No more content to load