Degen Dwight Schrute 🔺

@svpino I’ve a simple solution for you, first. Type /context to see how much tokens you use one your current session, after this check if the eye is focused on a document open or not. If yes click to have the mask of the file. After, type compact then check again the context.

I'm on a MAX plan, and now I'm hitting my limit every couple of hours. What's going on? Honestly, this makes Claude unusable. I've had to sign up for ChatGPT again just because of this.

@svpino Same problem. All 5 hours hitting after 2h.

@aryanXmahajan I wait for it 🙌

@aryanXmahajan SKILL

Claude Skill + Gamma + Apollo = AI Due Diligence Engine that replaced $50,000 in consulting fees... This system runs enterprise-grade company analysis in 7 minutes with research that firms charge $25K-$50K for... → No more analysts pulling data for 3 weeks straight → No more $300/hour lawyers reviewing standard templates → No more risk domains missed because nobody has bandwidth → No more decks that take a week to build and still look generic Just enter a company name + domain → full scored verdict delivered automatically. Here's how it works: → Firecrawl scrapes 8 company pages in parallel (security, legal, pricing, trust) → 11 Perplexity queries fire simultaneously across every risk domain → Claude synthesizes a scored GO / NO-GO verdict with red flags + negotiation leverage → Gamma auto-generates an 11-slide deck in the company's own brand colors → Full run log saved with cost breakdown + Gamma link Built with enterprise procurement standards. Runs in under 7 minutes. $1.50 per run vs $50,000 per engagement. One enterprise team cut their vendor onboarding from 6 weeks to same-day decisions. Want the complete Claude Code skill? Like + comment "SKILL" + repost, and I'll DM it to you. (must be following)

@svpino Damn! 🥲

Whoever uses AI to write code should be ultimately responsible for that code and liable for any potential consequences of running that code. I don't care what model you used, how you used it, or how much it helped you. Humans bear full responsibility.

@TreeNewsFeed Traders at WallStreet when they read this. 🥸

IRAN'S PARLIAMENT SPEAKER SAYS 'FAKE NEWS' USED TO MANIPULATE OIL MARKETS - RTRS

The difference between my dachshund and this administration? My dachshund never created a national security vulnerability to prove a point. And he was much cuter doing it.

Best part: the Pentagon is still using Claude on classified networks during active operations in Iran. “National security threat” on Monday, indispensable targeting tool on Tuesday. My dachshund was at least consistent in his hatred of the telephone.

My dachshund (rest his soul) had a ritual: every time the phone rang, he’d sprint across the living room, jump on the piano, grab the cord and attack it while barking like a maniac. He never once picked up the phone.

Pentagon considering replacing its $800B defense strategy with a Magic 8-Ball. Sources say it would be “a significant upgrade in predictive accuracy” over current leadership. In related news, the White House communications team has been offered a full-time content deal by

No plan to reopen Hormuz. No exit strategy. No theory of victory. 25% public approval. Diesel choking the global economy. Allies burning. And the NYT just now figuring out that “the administration miscalculated Iran’s response

If you pitched the current Iran war as a TV script, every studio would reject it for being too unrealistic. A thread 🧵