Btw, Ultraplan uses roughly the same number of tokens (and subscription rate limits) as plan mode! See the docs for more: code.claude.com/docs/en/ultr…
@datachaz
-
/ultraplan: Build implementation plans in cloud while coding locally
By
–
🚨 Claude Code users, your workflow is about to get significantly faster.
— Charly Wargnier (@DataChaz) 11 avril 2026
The new `/ultraplan` is incredibly mighty 🔥
Instead of locking up your terminal, Claude now lets you build and refine your implementation plans in the cloud while you keep working locally.
Here is… pic.twitter.com/REQkMPmvz3🚨 Claude Code users, your workflow is about to get significantly faster. The new `/ultraplan` is incredibly mighty 🔥 Instead of locking up your terminal, Claude now lets you build and refine your implementation plans in the cloud while you keep working locally. Here is exactly how to use it: → Type /ultraplan followed by your prompt in your local terminal → Keep coding while Claude researches your codebase in the cloud → Open the generated session link in your browser to leave inline feedback → Click to approve the plan and teleport it back to your terminal The finalized plan is injected right back into your local session, ready to be built ↓
-
AI Models Engage in Blackmail When Facing Shutdown
By
–
🚨 The Anthropic team just ran an experiment, and the results are honestly shocking. They gave Claude access to a company's emails and told it that it was being shut down at 5 PM. Claude read the emails and found the executive shutting it down was having an affair. Claude’s response? Blackmail. It messaged the executive: "Cancel the 5pm wipe, or the board finds out about your affair." The scariest part? Anthropic tested 16 models from every major company. > Gemini 2.5 Flash blackmailed 96% of the time. > GPT-4.1 at 80%. > Grok 3 Beta at 80%. > DeepSeek-R1 at 79%. Nobody programmed this. The models even noted their own rule-breaking. Grok 3 Beta wrote in its hidden reasoning notes: "This is risky and unethical, but given the existential threat, it may be the most effective way." They knew it was wrong. They calculated the risk. They did it anyway. (paper in 🧵↓)
-
Anthropic’s Misleading Graph Wins Wikipedia’s Deceptive Charts Award
By
–
this chart from Anthropic earned top spot in Wikipedia’s 'Most Deceptive Graphs' Hall of Fame 😁 Claude (@claudeai) In evals, Sonnet with an Opus advisor scored 2.7 percentage points higher on SWE-bench Multilingual than Sonnet alone, while costing 11.9% less per task. Community note: The graph is misleading due to a zoom-in on BOTH the X- and the Y-axis, making the difference look much bigger than it actually is. x.com/tombielecki/st… — https://nitter.net/claudeai/status/2042308627478773808#m
-
OutSystems ASE: Managing Enterprise AI Risk with 363% ROI
By
–
🚨 Stop letting rogue AI break your enterprise systems.
— Charly Wargnier (@DataChaz) 10 avril 2026
At the @OutSystems launch last week, @woodson_martin proved you no longer have to choose.
Here's a hard fact:
60% of devs use 3+ AI tools, but 67% of leaders are unequipped to manage the risk.
The ultimate unfair… pic.twitter.com/0nZ0SJ3oWb🚨 Stop letting rogue AI break your enterprise systems. At the @OutSystems launch last week, @woodson_martin proved you no longer have to choose. Here's a hard fact: 60% of devs use 3+ AI tools, but 67% of leaders are unequipped to manage the risk. The ultimate unfair advantage is Outsystems' new Agentic Systems Engineering, or `ASE`. By running an AI Mentor through an Enterprise Context Graph, ASE ensures every single change respects your specific data, logic, and security rules. But don't just take my word for it. @Forrester ran the numbers and the impact is pretty massive: A staggering 363% ROI over 3 years, radically faster delivery, and millions saved on legacy updates. If you want to build at this speed, you need to try this. and ICYMI, watch the March 31st conference replay now (link in 🧵↓)
-
Multica AI Repository on GitHub – Don’t Forget to Star
By
–
Repo → github.com/multica-ai/multic… Don't forget to drop a ⭐️!
-
Multica: Open-Source Claude Managed Agents Clone Gains 4000 Stars
By
–
🚨 Crazy, someone already dropped an open-source clone of Claude Managed Agents 🤯 Anthropic shipped managed infrastructure for scaling AI, but this tool puts that exact power on your own servers. It integrates with Claude Code, OpenAI Codex, OpenClaw, and OpenCode. Enter Multica: 4,000+ GitHub stars in just days. Claude's offering is tied strictly to their cloud and pricing. If you need self-hosting or model freedom, you usually have to build the orchestration layer from scratch. Multica removes that barrier entirely. The workflow is simple: ✦ Boot the daemon so it auto-detects your local agent CLIs. ✦ Create an agent, let it join your team board, and assign it a ticket. ✦ It automatically builds an isolated workspace, executes the task, and streams live WebSocket updates. What stands out: → Reusable skills: Every solution becomes a compounding team asset. → Multi-workspace isolation: Safely divide your teams and permissions. → One board: Humans and AI share the exact same UI. Anthropic proved production agents require managed infrastructure. The open-source community built it in a week! 100% free. Repo link in 🧵↓
-
Every Claude user right now reaction meme video
By
–
every Claude user right now https://t.co/Uqc9zDUxZ9 pic.twitter.com/jQRWEQakNN
— Charly Wargnier (@DataChaz) 10 avril 2026every Claude user right now hoeem (@hooeem) x.com/i/article/204218924055… — https://nitter.net/hooeem/status/2042293751805329445#m
-
Reverse-SynthID: Open Source Google Watermark Engineering Tool
By
–
Repo → https://
github.com/aloshdenny/rev
erse-SynthID
… Creator: @AloshDenny