benmurphy.eth

“Blue Eclipse” We’ve mapped the stars more clearly than we’ve mapped our own oceans. Nearly three–quarters of this planet is water, yet most of it remains unseen, untouched, and unknown; a world more mysterious than the galaxies we point telescopes at. There’s something humbling in remembering that beneath the surface are entire landscapes, ecosystems, and stories we’ve barely begun to understand. And still, the ocean is what keeps us alive. It regulates our climate, produces most of the oxygen we breathe, and shapes the rhythm of life on Earth. The deeper we look, the more we’re reminded that our survival is tied to this blue world; fragile, powerful, and largely undiscovered.

@perplexity_ai I've been trying to resolve a billing issue for weeks and I'm hitting a wall with your AI support system. The issue was supposedly escalated to your billing team on March 6th and I've heard nothing since. Happy to share my account details and the full thread via DM. Thanks.

Claude Opus 4.7 is now the default orchestration model powering Computer. It's also available for Max subscribers on Perplexity web, iOS, and Android.

. @perplexity_ai I've been trying to resolve a billing issue for weeks and I'm hitting a wall with your AI support system. The issue was supposedly escalated to your billing team on March 6th and I've heard nothing since. Happy to share my account details and the full thread via DM. Thanks.

Vote for TIME! We’re nominated for Best Magazine/Publication and for Best Mobile User Experience in the The Webby Awards. Cast your votes here ⬇️ - Magazine or Publication: lnkd.in/gpEmTWsK - Best Mobile User Experience: lnkd.in/gCrvTQrv

@mckaywrigley Sounds intriguing. Am interested.

looking for a handful of people to test something new... i've been using it for a few months and am prepping to share. if you're a fan of claude cowork, openclaw, manus, perplexity computer, etc then you're a perfect fit. this will self destruct in 4hrs - please dm or reply.

@TechWith_Nova BANANA

Claude Code + Nano Banana 2 is f*cking cracked 🤯 I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot. One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts. Then fires it off to Nano Banana 2. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot. If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ... This skill fixes the entire output: → You describe what you want in plain English → Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it) → Fires it to Nano Banana 2 via API → Saves the prompt + image in organized folders → You iterate on the style until it's dialed, then every output matches No more slot machine prompting. No more inconsistent brand imagery. No more burning credits on unusable generations. What you get: - Photo-realistic product shots and lifestyle images on demand - Full control over style, lighting, composition, and camera settings - Saved JSON prompts you can reuse across every campaign - A skill that gets smarter the more feedback you give it Built 100% in Claude Code with a custom skill + Python scripts. I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself. Want the full playbook? > Like this post > Comment "BANANA" And I'll send it over (must be following so I can DM)

@mikefutia IMPROVE

Self-improving Claude Code skills are f*cking ridiculous 🤯 One loop → 10 test runs, scored against an eval, prompt rewritten, retested, winner kept. A hook writer skill went from 32/50 to 47/50 overnight. All inside Claude Code. Perfect for DTC brands and agencies who have built Claude Code skills but the output is still inconsistent — great 70% of the time, unusable the other 30%. If you've been manually tweaking your skill prompts one run at a time, re-reading outputs, adjusting instructions based on vibes, and never quite getting the consistency you need... This method eliminates the entire loop: → You define 3-5 binary eval criteria for your skill → Claude runs the skill 10 times with varied inputs → A separate evaluator scores every output against your criteria → It identifies the most common failure patterns → Rewrites the skill prompt to fix what's failing → Retests and keeps the winner → Repeats until the score plateaus No manual prompt tweaking. No reviewing every output by hand. No "it worked that one time but I can't reproduce it." What you get: → A skill prompt that's been through 50+ automated test runs → A scored improvement log showing exactly what changed and why → Eval criteria you can reuse every time you update the skill → A method that works on any skill: hooks, briefs, ad copy, scripts, reports Inspired by @karpathy's auto research repo, the same loop AI labs use to improve their own models, applied to your creative workflow. I put together a full playbook showing how to set up the eval, the exact Claude Code prompt for the improvement loop, and starter eval criteria for the 5 most common DTC creative skills. Want the playbook for free? > Like this post > Comment "IMPROVE" And I'll send it over (must be following so I can DM)

@WorkflowWhisper PLAYBOOK

I built 31 automations for clients last year. Every single business needed some version of the same ones. So I put them all in one playbook: ✅ 31 workflows organized by department ✅ The exact prompt to build each one ✅ Which 3 to start with (save 10+ hrs/week) ✅ From "I should automate" to running in minutes Comment "PLAYBOOK" and I'll DM it to you.

@WorkflowWhisper PLAYBOOK

I built 31 automations for clients last year. Every single business - from solo founders to 50-person teams - needed some version of the same workflows. So I documented all of them. Every workflow. Every department. And the exact plain-English prompt that builds each one in minutes. Sales & CRM: lead capture, follow-up sequences, deal tracking, proposal generation, pipeline alerts Marketing: social scheduling, email sequences, content repurposing, UTM tracking, review requests Operations: invoice generation, payment reminders, inventory alerts, automated reporting Customer Success: onboarding emails, NPS surveys, churn detection, support routing Admin: meeting scheduling, expense tracking, document generation, approval workflows Each one includes the specific prompt I use to build it - not vague instructions, the actual sentence I type. Plus which 3 to start with if you want to save 10+ hours/week immediately. Comment "PLAYBOOK" and I'll DM you the full PDF for free.

@MicahBerkley I’m using getdewey.co Can do X and other platforms. Other platforms as well. When I have some time I’m going to export from there into an Obsidian second brain and put into a database I can use AI to chat with.

Before I build it, does anybody have any really good recommendations on tools that allow you to search and auto-folder your bookmarks. You have one hour to respond. lol

@adaptiveai Adaptive

Introducing Adaptive Computer. We put AI inside of an always-on personal computer that it uses to get work done. Schedule agents. Create software. Automate anything. As part of the launch, we’re giving one free month of Adaptive to users. Retweet, like, and comment ‘Adaptive’ to get it.

@lukepierceops BLUEPRINT

Automation consultants charge $15K for what Claude Code now does in 2 hours. I know because we're the ones who used to charge it. Here's the exact process: Step 1: Discovery (20 min) → Paste your org chart, tool stack, and top 3 bottlenecks → Claude interviews you with clarifying questions → Outputs a full process inventory ranked by time cost Step 2: Workflow Mapping (15 min) → Describe any department's daily operations in plain English → Claude builds a complete process map → Every manual handoff, redundant step, and automation trigger flagged Step 3: Opportunity Audit (10 min) → Feed it the workflow map output → Returns your top 10 automation opportunities → Ranked by ROI, complexity, and build time Step 4: Architecture Design (20 min) → Claude designs the full system architecture → Which tools connect where, what the data flow looks like → Agents for complex logic, linear flows for the repetitive stuff Step 5: Build (ongoing) → Claude writes the actual workflow JSON → Self-documents everything as it builds Step 6: The output. A live dashboard your whole team can work from. → Clickable process maps for every department → Automation opportunities ranked by ROI → Implementation progress by phase → KPIs updated in real time → One link you share with clients, freelancers, or your team to execute This is what we hand every client at the end of discovery. The .md file is what makes all of it possible. Without it, Claude guesses. With it, Claude builds like a $15K consultant. Like this post, RT and comment "BLUEPRINT" and I'll send you the full prompt stack and the .md file we use internally. (Must be following so I can DM you) 🎁 Bonus: The first 100 people get a real Precision AI Blueprint — an actual sample audit doc from a client engagement so you can see exactly what the output looks like.

@chddaniel @claudeai SHIPPER

BREAKING: @claudeai just got a huge upgrade today and I'm very happy to put it together in shipper. As of now, Claude Opus 4.6 can create self-building companies for you. We just launched Shipper 2.0 a power-up that lets Claude: ✅ Build web/mobile apps and Chrome extensions ✅ Code, design, monetize, launch ✅ Do email marketing ✅ Self-maintain the business Opus 4.6 can now do all the above from a <10 word prompt and for as low as $0.12/app... What used to take hours and hundreds of thousands in salaries now simply takes 1 prompt. Go in Shipper and ask Claude to "build a talent hiring platform" or "a calorie tracking app like MyFitnessPal". To celebrate, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)

@johnknopf @base Did you make this with AI assistance? There's a Ratchet & Clank joke in here somewhere. 🤣 But seriously, congrats. This looks cool!

1// gm. i built a token launchpad on @base. it’s called ratchet. the idea is to simplify it all and give creators a way to launch tokens where they can earn without having to dump on their community. ⬇️

Me and my NFT collection.

Hang it in the Louvre. #SeizeTheMoment

Best vibes on the planet. #SeizeTheMoment

This video is a perfect encapsulation of what the 90s were like.