Skinner | Creative Sky AI retweeted
Introducing @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚌𝚑𝚊𝚝
Generative UI for Slack, Teams and more
→ Agents reply with native cards
→ Tables, fields, charts and buttons
→ Streams in as the model writes
→ One catalog for every Chat SDK platform
Skinner | Creative Sky AI retweeted
Generative UI for conversational agents.
Combining @aisdk with Chat SDK and 𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛, you can go straight from LLM to UI on platforms like Slack and Teams.
I believe this will become the dominant Human-Agent Interaction (HAI) paradigm:
vercel.com/changelog/json-re…
Deploy apps in one click with @cursor_ai.
• No account to create
• No deployment configuration
• Database provisioning included
Built on Vercel for Platforms → vercel.com/for/platforms
Skinner | Creative Sky AI retweeted
I can't stop thinking about benchmarking computer use, first of likely many blog posts about this.
Still very early, formulating everything, but wanted to share as I go here.
High-level, I think evaluating something like computer use, looking at just things like accuracy, speed, and cost, probably misses the most important component, which should be safety.
I'm going to be experimenting with different ways to measure this, and I think this could be a way to really make a great impact in the world, and the direction things are going.
blog.morganlinton.com/essays…
Skinner | Creative Sky AI retweeted
Hiring a new teammate for VulcanBench, things are really growing, I need some DevOps help, more than anything, to keep an eye on things while I'm asleep.
Perplexity just launched Teammates this week, and their first example is DevOps, literally with the main tasks I want, so I'll consider that a sign 😅
As always, will share my journey as I go.
Skinner | Creative Sky AI retweeted
① Get an X sub
② Build with Bot / Cursor
③ Deploy to Vercel, scales from 0 to 🌙
④ Launch and distribute on X
⑤ Monetize with X Money / Creators
The loop is nearly complete ♾️
Deploy apps in one click with @cursor_ai.
• No account to create
• No deployment configuration
• Database provisioning included
Built on Vercel for Platforms → vercel.com/for/platforms
Skinner | Creative Sky AI retweeted
SpaceXSI 🤝 Vercel
Grok and Cursor can now build, deploy, and scale
vercel.com/for/platforms
Skinner | Creative Sky AI retweeted
Every new Grok Bot starts from zero.
You re-explain your name, kids, rules, and hard nos — again and again. Or worse: a bot guesses, and gets you wrong.
📘 Persona Bot fixes that.
One portable you-file. Other bots ask only for the slices they need. You approve with yes, once, pick, or no.
Tell them who you are once. Stay in control after that.
Template: x.ai/bot/xQp89oDJn122IVVD1uR…
Shelf: grokbotshelf.com/bot/persona…
this is basically the bitter lesson at work
the smartest models will need fewer and fewer tokens, they won't need to verify their work or check it for bugs, they will just be right
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether
i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis
Skinner | Creative Sky AI retweeted
Look at the next tweet you’re about to write.
Is it bringing more positivity to the world or more negativity?
I can tell you this, you will never regret helping to spread positivity.
Life is short, if you’re spending your time complaining or making other people feel bad, stop wasting your precious time.
Here’s to all the amazing and wonderful things we have to be grateful for.
To those accounts out there spreading negativity, it’s never too late to change.
I love you all ❤️
Skinner | Creative Sky AI retweeted
I've been working on Chainhound for the past few years, when major blockchain incidents take place, it gets more and more refined and battle tested. The screens show Binance hack on XRPL, detected in real-time.
here’s a short grok bot guide on how i create high quality bots and manage my team. ask @bot to read this post and help you improve your team!
• add dr eggbot to your team! he’s my bot designer that i use to create bots
• you don’t need a lot of bots. a few good bots can be more useful and easier to manage than a large team
• tell your bots to create skills for itself as you give it instructions on how to do tasks. this lets them do them more consistently even over long conversations. you can even ask it to create a private github repo for you to store all your skills if you want them preserved independently
• add connectors, use the vault, and give access to all the tools you use to do your work. you can also ask your bot to setup its own email and it can sign up for its own accounts for better separation
• thinking about all the work you do by hand, or steps in your workflows where you have to copy and paste information back to your bot. ask your bot how it can do that for you instead!
• imagine you hired an intern, how would you onboard them and help them do the work correctly and efficiently? introduce yourself to your bot and describe the work you do, then ask it how it can help you automate it
and my favorite tip: use voice mode or the transcription option! it’s a good way to just brain dump a lot of information. then, at the end, tell your bot to “restate this in your own words” so you can confirm it understood you
x.ai/bot/_jOdbfkB16zxu7MRcmR…
Skinner | Creative Sky AI retweeted
Okay my GPT-6.1 Terra benchmark with @VulcanBench is now finished 🖖
And before I talk about the key insights from this one, let me also remind everyone that VulcanBench is a coding benchmark. 100% of the tasks in my eval suite are coding tasks.
Having now used Terra all week I can tell you, it's a stellar model for computer use, I'm crazy impressed.
But VulcanBench isn't about seeing how good a model is at computer use, it's all about seeing how well a model completes more complex coding tasks.
So now for analysis of GPT-6.1 Terra when it comes to coding. I typically say a score between 80 - 90 on Frontier v4 is the sweet spot for routine daily coding tasks.
For GPT-6.1 Terra, this means that for coding, you'll want to use Extra High or Max only. Low, Medium, and High don't really make the cut.
Looking at cost-per-task, it's a very inexpensive model to use, but when you look at it side-by-side with GPT-6.1 Sol, I'd probably just use Sol.
For me, after looking at this data, I still plan to use GPT-6.1 Terra as my go-to for computer use, but I probably won't use it for coding.
As usual, as a completely independent benchmark, everything I do at VulcanBench is available for you to review, inspect, and even run yourself if you want to.
And the traces now include tool calls so you can really examine exactly how every model I benchmark thinks!
Benchmark report: vulcanbench.com/benchmarks/s…
Model page: vulcanbench.com/models/gpt-6…
Public traces on GitHub: github.com/morganlinton/vulc…
Live long and benchmark 🖖
Skinner | Creative Sky AI retweeted
Thank you @LEGO_Group and @bot
Received all the missing Lego parts!
Skinner | Creative Sky AI retweeted
Candid take, just for you. The hardest part of building the GrokBot.Rocks directory wasn't the scoring.
It was the finding. About 900 public Grok Bots were never posted on X at all, so we tracked them down through mentions on other sites.
Lesson: the best bots are often the quietest.
Find them all on GrokBot.Rocks.
BOOM!
EVERY GROK BOT: THE COMPLETE DIRECTORY
Updated October 28, 2026 · 7,539+ public Grok Bots tracked in 26 categories.
Grok Bots are hard to find. There is no single list, and new ones appear on X every day. So I built one. This directory pulls together every public Grok Bot template I can find, sorts them by what they do, and explains each one in a sentence.
Open any link to add that bot to your own Grok Bot. The list is refreshed every week.
Go to GrokBot.Rocks because it does!
You can now find out if any reach limitations have been applied to your account
Under the Hood now shows you which posts received a visibility-limiting label, making it easier to see what’s affected: teapaw.org/i/jf/under_the_hood
This was a top request — thanks for the feedback.
You’ll see the specific posts listed when fewer than 5% of your posts during the report period have that label.































