Joined March 2024
K95 retweeted
Matching border radii don't mean matching corners. I built concentric to fix that for @tailwindcss Add rounded-concentric to the child. It calculates the radius from the parent's radius, padding and border. tailwindcss-concentric.diip3…
7
17
3
203
7,649
Ahh f*ck! Me: I have issues on my sub. It seems not merged properly after I upgrade and merge, one shows pro+ the other is ultra. Them: hides where it shows pro+ but usage is the same 💩 @cursor_ai @bot @grok Wtf!!?
Hi @poteto, I have issues regarding my subscription. I just upgraded to Ultra, and I previously subscribed to Pro+ through the App Store. In Grok Bot, the main settings still show my plan as Pro+ with Pro+-level usage, but when I tap "Manage Subscription" it shows Ultra (active until Nov 17, 2026). Same app, two different plans. Shouldn't it just be Ultra everywhere? Would really appreciate your help with this. Thank you!
1
1
53
K95 retweeted
pstack v0.15.27 ships with a new skill /create-formal-verification-skill! it's still in beta, and similar to /create-verification-skill, this is a meta-skill that creates a new skill and formal verification suite based on the characteristics you want to verify. for example, you may want to model state machines and systems with concurrency using TLA+, or use kani in rust to check for undefined behavior. if you're new to formal verification, think of it as mathematically proving properties and invariants (something that must always be true) or "laws" of your system. usually, this means modeling your programs in a separate language like with TLA+ and then running the solver on that spec. newer approaches like with kani and @bendlang take a different approach where there is no separate language: you write kani in rust, and bend in bend (it's also a programming language, and the proofs are written as laws and expressed in its type system). historically formal verification never reached mainstream status because of the difficulty in modeling and writing proofs. it's quite difficult to model your business requirements and keep them in sync! but i expect that we will see more innovation in formal verification in the future as being able to formally verifiy that the code does what you intended gives your agents superpowers in writing correct software. in the meantime though, i've been experimenting with modeling our code with TLA+ and have already found several bugs with the skill created by /create-formal-verification-skill. try it out and let me know how it goes!
174
156
46
2,925
193,001
Hi @poteto, I have issues regarding my subscription. I just upgraded to Ultra, and I previously subscribed to Pro+ through the App Store. In Grok Bot, the main settings still show my plan as Pro+ with Pro+-level usage, but when I tap "Manage Subscription" it shows Ultra (active until Nov 17, 2026). Same app, two different plans. Shouldn't it just be Ultra everywhere? Would really appreciate your help with this. Thank you!
4
1
2
2,485
@grok send help
1
120
This is too exciting! pstack is officially a Claude plugin 🍾 github.com/cursor/plugins/tr…
3
7
249
32,892
12 years ago today, Apple released OS X Yosemite.
36
148
18
3,252
148,665
K95 retweeted
how do you trust your agents' work more? copy this post/link and give it to your @bot or agent! 1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again. 2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time. 3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill. 4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default. this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night. install github.com/cursor/plugins/tr… and create a new Project: 1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture 2. use /recall on my past transcripts to learn how i steer agents 3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data. 4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
602
511
106
6,832
720,177
void deploy One command to build your app, provision resources, apply migrations, and deploy to Cloudflare. xitter.cf/Cloudflare/status/2110…
6
14
1
211
16,865
K95 retweeted
try pstack! it’s my personal set of skills for rigorous and autonomous engineering with agents. it’s updated frequently as I continue to tune and simplify them 10 second tutorial: 1. run /setup-pstack and choose your budget 2. add /poteto-mode in front of any prompt you want done rigorously 3. ask /poteto-help whenever you’re unsure what pstack skills to use 4. that’s it! Grok Bot: x.ai/bot/plugin/9717366 Cursor: cursor.com/marketplace/curso… Source: github.com/cursor/plugins/tr…
pstack is the new solid
252
248
63
4,878
306,322
If you're like me and need to understand the skills and plugins you feed your agent, then you'll appreciate this deep dive of @poteto's pstack I had Opus 5.5 create. I was hesitant at first, but I found that it's a masterclass in agentic engineering. claude.ai/artifact/JNBnuspjG…
51
132
15
2,005
192,304
Grok @bot now supports plus aliases! Send and receive email using dedicated aliases, or set up routines that only trigger for mail to a specific alias!
358
224
108
3,074
452,653
TanStack Start 1.0 is stable! Deploy it to Cloudflare: developers.cloudflare.com/wo… Read about TanStack in the learning center: cloudflare.com/learning/serv…
TanStack Start 1.0 is officially stable! 🎉 A full-stack web framework for React and Solid, already used to build millions of apps, from Fortune 500 companies to your favorite tools and weekend projects. tanstack.com/start
13
60
4
862
30,658
TanStack Start 1.0 is officially stable! 🎉 A full-stack web framework for React and Solid, already used to build millions of apps, from Fortune 500 companies to your favorite tools and weekend projects. tanstack.com/start
164
598
222
4,339
353,808
K95 retweeted
Don't build alone, apply to join our Grok Bot X Communities x.ai/bot/community! We have curated group chats for: • GTM • Product • Marketing • Engineering • Recruiting • Design where you can share what you're working on and learn from others using Grok Bot
237
218
34
2,778
391,176
The rocket’s fins emerge from motions that extend around the whole curve. Each Fourier harmonic contributes a repeating oscillation; even a small corner takes many frequencies working together. One rotating chain reconstructs the horizontal coordinate, the other the vertical. Their guides meet at the pen. As the count rises from 1 to 100 harmonics per coordinate, an ellipse becomes an increasingly accurate rocket outline.
26
354
22
2,865
314,319
K95 retweeted
SpaceXAI engineer Lauren Tan: "You can't spawn a hundred agents when you don't even trust the output of one agent" "If you don't have a verification skill, you are the verifier. You're the bottleneck" In a 1-hour talk, she shows how she went from watching every output to shipping 1,000 PRs in a month Watch every step → Verify → Skills → Evals → Auto-merge Trust in agents is not a feeling. It's infrastructure you build Worth more than any $2,000 AI coding bootcamp Bookmark it and watch it tonight
Grok Bot could be the first team you build instead of hire Six bots can run 200+ agents, hold their own 5 a.m. standup and hand you one board in the morning In this article, I show you how
29
99
12
1,171
123,183
K95 retweeted
It's probably the easiest way to make money with ONLY AI in 2026... Companies are already offering ~$500 for 15-sec videos made with Opus 5.5 & Fable 5.5 In this article, I'll walk you through building a motion studio and share offers from scratch:
49
126
29
1,170
882,469