Pinned Tweet
I made Say for Codex.
Type `/say` after an answer and Codex reads it aloud locally on macOS.
No API key.
No sending text to a TTS model.
No pasting long reports back into chat.
Useful when you want to listen while reading, or review long agent output hands-free.
Link below.
skills.sh/botanium/say/say
Botanium retweeted
Every founder should know what their startup is worth, even if they have zero plans to sell.
Imagine you're running a SaaS doing $1.5M in ARR and $500K in profit.
Business is good and you're paying yourself well.
Then one random Tuesday, someone emails you offering $3M to buy the company.
Sounds pretty exciting!
But is $3M a great offer or should you counter at $5M?
Would another buyer pay $6M?
Is $3M actually more than the business is worth?
You'd be surprised how many founders have absolutely no idea.
And I totally get it.
When you're busy building a startup, thinking about selling it probably isn't at the top of your list.
But understanding what buyers value can also help you build a better business.
Maybe your margins need work.
Maybe too much revenue comes from one customer.
Maybe the entire company falls apart if you take a two-week vacation.
These are things worth fixing whether you sell next month or ten years from now.
Spend a little time understanding what your startup could sell for.
You might be sitting on a much more valuable asset than you realize.
P.S. thinking about selling your startup? Our team will help you understand what your business is worth, prepare it for buyers, and guide you through the entire acquisition process. Meet the team here: acquire.com/guided-by-acquir…
Botanium retweeted
We’re excited to introduce the Muse Wonder series with Muse Wonder and Muse Wonder Full, our most capable models yet. Both are frontier models, built to deliver state-of-the-art performance for personal and professional agentic tasks.
Muse Wonder is available today via the Meta Model API and Muse Code. Muse Wonder Full is available today for Muse Code subscribers. Muse Wonder will also soon power experiences in our personal agent product, Muse, rolling out first to subscribers.
Today I have been trying to get GPT Astra to do some Today I spent far too long trying to get GPT Astra to perform a simple task in our ERP system: updating a few dates. It refused repeatedly and kept asking for supporting documents, even though the task was straightforward.
This kind of unnecessary friction makes me want to stop using ChatGPT, cancel my subscription, and switch to a model that actually helps me get work done.
@thsottiaux
Botanium retweeted
i now have chatbase.com. it was previously owned by google.
Grok 4.5 it is something else, it is exteamly good, especially when you set up with Codex for review.
Botanium retweeted
Always 🧡
I'm grateful for @coderabbitai sponsoring so many open-source developers 👏 This is what every software company should do for every software company is built on top of hard, unpaid, and thankless work of thousands of devs with a dream out there.
Go sponsor your dependencies! 🏃♂️
I built a tiny Codex skill for local read-aloud on macOS.
It lets Codex read answers, clipboard text, and Markdown files aloud using macOS speech, no API key needed.
Useful for cognitive offloading: read + listen at the same time.
GitHub:
github.com/Botanium/codex-sa…
Botanium retweeted
Your vibe design partner just got more collaborative!
To celebrate I/O, here are 5 major upgrades (and one big bonus!):
🌊 Streaming
📄 Start with your existing design
⏩ In-place AI Edits
🎥 Motion on HTML-native Canvas
🚀 More Import / Export Options (.fig, Netlify, Loveable, Bolt)
🌟 BONUS: Import and sync your codebase
Rolling out now. Details and product walkthrough video in 🧵
Botanium retweeted
Nemotron 3 Ultra was launched today, including a focus on low latency agentic performance. We tested it against peers under restricted turn-usage limits on Terminal-Bench v2.1 - @NVIDIA Nemotron 3 Ultra completes tasks at a much faster pace than peers due to its high inference speed while scoring competitively on the benchmark.
In this analysis each model is given a ‘turn limit’ within which it can complete tasks, inside a customized version of the Terminus 2 harness which advises it of this limit. We apply 4 increasing turn limits and trace each result’s tradeoff of task latency and performance. Time per task, on the X axis, is calculated as decode time based on token usage and measured endpoint output speeds (for Nemotron 3 Ultra, speeds were measured on a pre-release deployment on @blackboxai), plus the actual time spent executing tools to complete the benchmark.
Nemotron 3 Ultra is the fastest across all turn limits and sits on the Pareto frontier for performance versus time per task for this evaluation.
Antigravity is really good lately, especially after the Google io.
We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻
It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows.
Full Antigravity CLI Walkthrough:
If GPT 5.5 doesn’t fix @openclaw , it will be unusable from now on. No matter what I try, I don’t get the same result as before.
He knows something that the rest of us don’t know it yet.
