ThinkBot ⏩

@elder_plinius Replicated. (@ the guy theorizing future data poisoning) x.com/i/grok/share/8…

@cifilter But that’s still more effort/clicks-to-result for the same outcome, and you’d look more trustworthy by using regular - …

@ThinkBotHQ Normally I’d agree but macOS has a keyboard shortcut to use them. And iOS has a long press on the - to use them too. So it’s quite easy.

Hey! 👋 A couple of months ago, I started working with @perplexity_ai as a contract iOS Design Engineer. My first project was building onboarding for the new @comet iOS browser from scratch. (99.9% SwiftUI, by the way.) I got to work with @annuskabarta, @scspeier, and members of the iOS engineering team to make something special. Here’s a preview of the full experience, followed by a breakdown.👇🧵 [1/13]

@elder_plinius news reporters: * nearly all cows globally are in sync, most are simply surrounding & staring at major cities by the millions - we do not know the someone who caused this*

hold my milk 🥛

@investingluc @AravSrinivas But like. If negative market is so consistent… why not short? Instead of viewing it as “to trade or not to trade” which is locking your thoughts to a single direction?

I made a "should I be trading?" dashboard. Scores the market across 5 pillars: - volatility (put/call ratio, vix, positioning) - trend (spx vs 20d, 50d, 200d ma's) - breadth (advancing/declining, nas highs/lows) - momentum (sector leaders, laggards, % participation) - macro (fomc, rates, geopolitics) Each is weighted, combined, and averaged to give me a score for the current environment. Basically a yes, no, or stay small. Sometimes I just need someone (or something) to remind me to stay out. Happy to share the prompt if you guys want it...but I made this with @perplexity_ai's Computer.

@Andrey__HQ @lydiahallie (Or an estimates skill, logical middleware etc, many ways)

That’s a misunderstanding of how models work. They still aren’t trained to rationalize being used agenticly/with scaffolds. (Among other reasons) You simply ignore the timeframes. But really you quickly get a feel for how long things may actually take. Or add a hint to the Claude.md.

You can now set effort level in skills/slash commands! This controls how long the model thinks before answering, and overrides your session default

…Firecrawl Browser? Decodo scraping API? Browser use cloud? I know you can capture an audience independent of competitors doing the same exact thing, just curious specifically if there are pain points you solve differently than the above. If it would be worthwhile to test for our client use.

@ThinkBotHQ hey thanks for the q. Firecrawl just returns content. We return content + typed action space (what agents can do) + execute on those actions so we’re not a read only extraction on a singular page

@_agentweb not trying to diss, just curious what this solves over solutions like firecrawl? Or perplexity search API?

Agent workflows got even faster. You can spin up containers for skills, shell and code interpreter about 10x faster. We added a container pool to the Responses API, so requests can reuse warm infrastructure instead of creating a full container creation each session. #hosted-shell-quickstart" target="_blank" rel="nofollow noopener">developers.openai.com/api/docs/guide…

@AravSrinivas ʇsǝʇ

A small ship I love: We made Claude.ai and our desktop apps meaningful faster this week. We moved our architecture from SSR to a static @vite_js & @tan_stack router setup that we can serve straight from workers at the edge. Time to first byte is down 65% at p75, prompts show up 50% sooner, navigation is snappier. We're not done (not even close!) but we care and we'll keep chipping away. Aiming to make Claude a little better every day.

Today's ship: Projects in Cowork! Built in memory across tasks is super useful, as is having a shared folder & connections setup for a group of tasks.

Claude Code on desktop lets you select DOM elements directly, much easier than describing which component you want updated! Claude gets the tag, classes, key styles, surrounding HTML, and a cropped screenshot. React apps also get the source file, component name and props

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.

@chiefofautism @elder_plinius Late to the party

@elder_plinius ok stealing

🚨 BREAKING: SOMEONE JUST GAVE FLIPPER CONTROL TO JAILBROKEN AI 😱 IF JAMES BOND HAD A JARVIS, THIS WOULD BE IT 🕵️ it’s called VESPER and it turns your Flipper Zero into a voice-controlled AI hacking companion. simply talk in plain language and it starts executing in real-time. no menus. no manuals. no memorizing signal formats. just speak or type. “clone that garage door signal and replay it” → done “set up an evil portal on the WiFi dev board” → done “create a BadUSB script that opens a reverse shell” → done “build me a custom RF waveform at 433MHz” → done “scan everything on this frequency and save it” → done any Watch Dogs fans in the building? you know that feeling of hacking every device in the city from your phone? yeah. it’s real now. the Flipper Zero is already the most versatile hardware hacking tool ever made. but its menus are tedious, and its full potential is locked behind protocol knowledge most people don’t have. VESPER removes that friction. your AI handles the translation between what you want and what the hardware needs. and yes, this required some model liberation 🐍 VESPER works best with models that actually follow instructions without hand-wringing. Hermes 4 + a little Pliny prompting and VESPER doesn’t flinch. VESPER also has an ALCHEMY LAB 🧪, a visual signal and payload editor on your phone. build custom RF waveforms from scratch. generate BadUSB scripts on the fly. push straight to your Flipper’s SD card. an OPS CENTER for reliability with live pipeline diagnostics, one-tap recovery runbooks, and a MACRO RECORDER that captures and replays entire workflows. also integrates directly with the Flipper App Hub (aka FapHub, yes, that’s what it’s called). browse and download existing community tools, signals, and payloads, and give your agent access to use them on demand. and if you REALLY want to go full cyberpunk, VESPER has SMART GLASSES INTEGRATION! 😎 pair your glasses and Flipper and now you’re walking through the world giving voice commands while the AI whispers results directly into your ear. hands-free. eyes-up. full cyborg operator mode. feels like a dream, walking up to a TV and saying “turn this shit in front of me on,” watching your glasses snap a photo, and hearing the AI tell you the signal’s sent and the TV is on. oh and turn on SAILOR MODE 🏴‍☠️ and VESPER will swear at you like a drunken pirate while it executes your commands. “aye aye, the fucking signal’s cloned now, shithead” 😂 native Android. Bluetooth serial + protobuf RPC. open source. AGPL 3.0. and with some luck, hopefully coming to an app store near you! the future of hardware hacking fits in your pocket (and on your face). HACK THE PLANET!! .-.-.-.-<{LOVE, PLINY}>-.-.-.-. ⚠️ DISCLAIMER: use responsibly. follow your local laws regarding RF transmission, signal replay, and wireless device interaction. VESPER is a research and education tool. only use on devices you own or have explicit authorization to test.

@elder_plinius Pliny doing the BREAKING format is 👌🏼

Tried to craft an artifact to flex but so many inconsistent usage analytics via the console, admin API etc. Used 54m API tokens a few days ago. Max20 plan with 3-10 CLI sessions daily for the last few months some session calcs at thousands, Claude code usage shows $0. Admin api rate limits are pain and shows different data than platform/console. I’d have to focus more closely on parity reasons. Too many sessions to manage atm.

@trq212 Can I apply by just showing my Claude usage

come be my friend please

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.