R.I.P. Higgsfield Katana.
I reverse engineered it and made a Claude motion design skill that replaces it.
Download the skill: https://t.co/MJubKL8z3b
> describe your product, game or brand in a few lines
> Claude writes, animates and cuts the whole film to the beat
> Scenario makes the music and sound effects, 4K out
Higgsfield influencers on Instagram kept promising the Katana setup to anyone who commented.
I commented on every one and only got a link to their landing page.
So I built it myself, and here it is.
Introducing Vela 3.0 📡 Name it. Vela finds it.
Six open models (0.3B–27B): decisions + the spans you name. One call.
⚡ 380M: #1 Decision Index ≤500M
🎯 Beats GPT-5-mini at zero-shot classification
🔍 18 ms per span question
🤗 https://t.co/F1fYdiSNzX
#Jev#Decison
Early Access is Live!
Just joined the @evmbot early access.
One agent to deploy, launch and trade on every EVM chain.
Apply Here: https://t.co/rqXyh1ihPQ https://t.co/1WXC2Y7Wt1
Entah ini bugs atau memang beneran gratis ya! 😅
Coba ini:
1. Install Zed Editor (https://t.co/yzBv61pnEK)
2. Setup akun "ChatGPT Subscription" melalui menu "Setting/User/AI/General/LLM Provider", lihat pada gambar.
3. Login menggunakan akun ChatGPT yang "Tidak memiliki Subscription".
4. Setelah itu coba Chat pakai "GPT-5.6-Terra".
Ditempat kalian bisa chat atau tidak?
Disini, ditempat saya bisa chat dengan leluasa menggunakan "GPT-5.6-Terra", padahal akun yang saya gunakan tidak memliki langganan sama sekali di ChatGPT.😂
Agent coding life hack:
1) Install omp and add openrouter as a provider (https://t.co/UBCVfGrfur).
2) Select the model as the currently free "stealth" model ox Alpha (https://t.co/h07jjhYx9R).
3) Install mcp_agent_mail_rust (https://t.co/YtCpddhXFH).
4) Create 3 instances of omp in the same project and tell them to do this:
"First read ALL of the AGENTS.md file and README.md file super carefully and understand ALL of both! Then use your code investigation agent mode to fully understand the code and technical architecture and purpose of the project.
Then I want you to study and then further polish/refine/improve/fix the UI/UX so it works as well as possible on both desktop and mobile browsers. Before doing anything else, register with MCP Agent Mail and introduce yourself to the other agents."
5) Profit (or at least enjoy those sweet, free tokens).
mau sharing kemarin malem dapet email untuk audit client yg make AWS & di awal w udh kasih opsi, buat dev env bisa ditaruh vps dan costnya flat around 5-8 euro per bulan dan kalau cloud kaya aws bisa up to 80 usd*, disini client heran kok buat dev doang "lumayan" dan w audit...
𝗛𝗲𝗿𝗱𝗿 has been great these past few days.
Claude and Codex each get a pane. The main agent assigns work, waits, reads, and follows up. I used to carry every conclusion between windows myself.
With ChatGPT, Codex, and other agents, one works and another reviews.
𝗣𝗿𝗼𝗺𝗽𝘁:
Run this task with multiple agents in parallel:
[TASK]
You are the coordinator. Check which agents and panes are available, then split the task only where pieces can move independently.
Give each agent one clear outcome. State the deliverable, how it will be checked, what it may change, and what it must not touch.
Research and review agents may share the current workspace, but they must stay read-only. For work inside a Git repo, give every agent that edits files its own worktree so no two writers share a checkout.
Use Herdr to assign work to the other panes, wait for their results, read their output, and follow up yourself. Do not ask me to relay messages.
When different agents are available, have one execute and another review. Swap roles on the next pass if useful. Settle factual disagreements with a test. You decide judgment calls.
Bring the work together in one place. For a Git repo, integrate through one checkout and rerun the real checks. Do not push, publish, touch production, or expose secrets without my approval.
Finish with the result, verification evidence, unresolved issues, and any panes or worktrees still running.