rmz 🌱🌐 - 🐺
2.2K posts
GPT-5.5 + GPT Image 2 in Codex is insane 🤯
The watch components generation + alignment was one shot.
English
@trq212 Good ideas but Still a gadget with some issue on copy pasting, back lines.
I would dream of a rust stack cursor like to manage Claude code session on different project (like the app but local)
Iykyk
English
Have you tried the new Claude Code renderer? What has your experience been like?
If you haven't, you can enable it with: CLAUDE_CODE_NO_FLICKER=1 claude
Boris Cherny@bcherny
Today we're excited to announce NO_FLICKER mode for Claude Code in the terminal It uses an experimental new renderer that we're excited about. The renderer is early and has tradeoffs, but already we've found that most internal users prefer it over the old renderer. It also supports mouse events (yes, in a terminal). Try it: CLAUDE_CODE_NO_FLICKER=1 claude
English
thanks! ntfy is a different thing (pub/sub alerts). notifyd is transactional, your app sends email + push + in-app to a user.
multi-channel: channels: ["email", "sms", "in_app"] in one POST.
Novu needs a workflow in their dashboard or their typescript framework for the same thing. makes sense for their enterprise customers who want a visual builder. didn't make sense for me, agents just wanted API or CLI currently.
English
Nice piece of infra, Novu feels heavy.
Have you looked at ntfy.sh?
Different angle (pub/sub) but same philosophy.
Curious how you handle multi-channel routing: email/push/in-app
rmz 🌱🌐 - 🐺@Rmzlb
i used novu for a while. works, but 500mb+ of ram and my agents couldn't manage it without fighting the react sdk and the mongodb/redis setup. rewrote the whole thing in rust. 30mb of ram, ~500 notifs/sec, one postgres database. one binary.
English
the thing that actually made the rewrite worth it. /docs/llms.txt. plain text api reference. my coding agent reads it, sets up templates and send calls on its own. no docs browsing, no integration guide.
that's what i couldn't do with novu.
3700 lines, mit, open source
English
i used novu for a while. works, but 500mb+ of ram and my agents couldn't manage it without fighting the react sdk and the mongodb/redis setup.
rewrote the whole thing in rust. 30mb of ram, ~500 notifs/sec, one postgres database. one binary.
English
rmz 🌱🌐 - 🐺 retweetledi
🚨 Screen Studio charges $89 for this. Someone open sourced the entire thing for free.
It's called OpenScreen. 8,400+ GitHub stars.
You record your screen. It automatically transforms it into a polished, professional demo video.
Auto-zoom into clicks. Smooth cursor animations. Motion blur. Custom backgrounds with wallpapers, gradients, and shadows. Webcam overlays. Annotations. Timeline editing. Export in any aspect ratio.
The exact workflow that Screen Studio sells for $89 and Loom sells as a subscription. Free. No watermarks. No accounts. No subscriptions.
Here's what you get out of the box:
→ Full screen or window capture with system audio and mic
→ Automatic zoom that follows your cursor and clicks
→ Manual zoom with customizable depth and timing
→ Smooth motion blur on pan and zoom transitions
→ Animated cursor rendering with motion effects
→ Webcam bubble overlay with drag-and-drop positioning
→ Wallpapers, solid colors, gradients, or custom backgrounds
→ Text and arrow annotations layered over recordings
→ Timeline trimming and variable speed segments
→ Crop, resize, and export in any resolution or aspect ratio
→ Save and reopen projects anytime
Here's the wildest part:
A developer forked it and built an even more advanced version called Recordly. Full cursor animation pipeline. Native macOS and Windows recording. Zoom behavior that mirrors Screen Studio frame-for-frame. Audio tracks. Webcam overlays with zoom-reactive scaling.
Both are free. Both are MIT licensed. Both work on Windows, macOS, and Linux.
Download. Record. Export. Done.
100% Open Source. MIT License.
(Link in the comments)
English
rmz 🌱🌐 - 🐺 retweetledi
Okay so I made an open source toolkit for the EU AI Act compliance.
Here's the thing, it's coming (it's already there in fact). GPAI rules kicked in August 2025. Full high-risk requirements hit August 2026. Fines go up to €35M or 7% of global turnover. And most teams I talk to still have no idea what tier their system even falls under.
So I built three things, same data layer, no vendor lock-in:
→ TypeScript SDK: classification, checklists, templates
→ CLI with an interactive classification wizard
→ Web dashboard with timeline + compliance tracking
14 languages supported in the web app.
One command to find out where you stand:
npx @ eu-ai-act/cli classify
Ah, also it's agentic native, so you can just install the skills and ask your favorite agent to use it ;)
Repo below 👇
English
rmz 🌱🌐 - 🐺 retweetledi
Can LLMs be PROVABLE computers?
Percepta showed that a transformer can BE a computer. Compiled weights, deterministic execution, 30k tokens/sec.
But nobody asked the obvious follow-up: how do you know it computed correctly?
So I built the verification layer. A STARK that proves it 👇
Christos Tzamos@ChristosTzamos
1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy
English
The 17% drop isn't from using AI.
It's from using AI without structure.
I've been coding with Claude Code daily for 6 months. The difference: I encode my review checklists, debug methodology and ship gates as agent skills.
AI follows MY process. Not the other way around.
Vibe coding = skill atrophy.
Encoded methodology = force multiplier.
English
Anthropic's own study proves Vibe-Coding and AI coding assistants harm skill building.
"AI use impairs conceptual understanding, code reading, and debugging abilities, without delivering significant efficiency gains on average"
Developers learning 1 new Python library scored 17% lower on tests when using AI.
Delegating code generation to AI stops you from actually understanding the software.
Using AI did not make the programmers statistically faster at completing tasks.
Participants wasted time writing prompts instead of actually coding.
Scores crashed below 40% when developers let AI write everything.
Developers who only asked AI for simple concepts scored above 65%.
Managers should not pressure engineers to use AI for endless productivity.
Forcing top speed means workers lose the ability to debug systems later.
----
Paper Link – arxiv. org/abs/2601.20245
Paper Title: "How AI Impacts Skill Formation"
English
The security vs convenience paradox is real.
Run agents on a VPS → safe, isolated, 24/7. But no browser sessions.
Run agents on your laptop → full Chrome MCP, live cookies. But your agent has access to everything.
Whoever solves "authenticated browser on a headless server" wins the agent infra game.
Petr Baudis@xpasky
Official Chrome MCP support is coming? I should be able to just `amp mcp add chrome-devtools -- npx chrome-devtools-mcp@latest --autoConnect` and let Claude browse on my behalf, within my login sessions. Chrome 144 required, it is in "early stable" mode and aiui will get general release only next Wed.
English
@Starknet just shipped STRK20. Any ERC-20 can now have private balances and transfers. Compliance built in. Hash-based proofs, no trusted setup.
Most people see a DeFi privacy upgrade. I see something bigger.
I used to run a warehouse. EDI orders on FTP servers. SAP IDocs failing at 3am. Master data mismatches that cost weeks to fix. One wrong product code stops the whole chain. Someone opens a CSV, finds a typo, sends three emails.
That's how trillion-dollar supply chains still work in 2026.
If ZK proofs can make tokens private AND verifiable, the same architecture solves the bullwhip effect. Orders proven cryptographically. No master data wars. No information asymmetry between partners.
Private doesn't mean hidden. It means proven without showing the data.
Not a DeFi feature. The biggest B2B infrastructure shift since EDI was invented in 1970.
Starknet (Privacy arc) 🥷@Starknet
1/ Privacy for Bitcoin… and for every ERC-20. Introducing STRK20: a privacy capability that gives any ERC-20 confidential balances and private transfers, with compliance built in. The market is now one click away from privacy on any token 🧵
English
@Gavriel_Cohen hmm no plans right now I believe but interesting @noahzweben
English
Il est temps d’annuler votre abonnement ChatGPT.
Sam Altman est un vendu qui vient d’accepter un accord avec le DoW à l’instant même où Anthropic ont eu le courage de dire non et de poser leurs limites.
OpenAI mérite d’aller à 0.
Sam Altman@sama
Tonight, we reached an agreement with the Department of War to deploy our models in their classified network. In all of our interactions, the DoW displayed a deep respect for safety and a desire to partner to achieve the best possible outcome. AI safety and wide distribution of benefits are the core of our mission. Two of our most important safety principles are prohibitions on domestic mass surveillance and human responsibility for the use of force, including for autonomous weapon systems. The DoW agrees with these principles, reflects them in law and policy, and we put them into our agreement. We also will build technical safeguards to ensure our models behave as they should, which the DoW also wanted. We will deploy FDEs to help with our models and to ensure their safety, we will deploy on cloud networks only. We are asking the DoW to offer these same terms to all AI companies, which in our opinion we think everyone should be willing to accept. We have expressed our strong desire to see things de-escalate away from legal and governmental actions and towards reasonable agreements. We remain committed to serve all of humanity as best we can. The world is a complicated, messy, and sometimes dangerous place.
Français