feyioz

Using Verdent AI (verdent.ai) for my coding workflows and its multi-agent architecture is an absolute game-changer! 🚀 Get 40% off via my link: verdent.ai/?ref=32YIGWOr enter code on your dashboard: 32YIGW 💻✨

@OrcaRouter Ending black-box dependency and putting full graph control in devs' hands via YAML is pure genius. Game-changing move! 🚀

Fable 5 is dead. We just resurrected it — cheaper, open and you hold the keys. OpenRouter dropped Fusion 48h ago and broke the internet. We tested it hard. The synthesizer is insane for deep research… but absolute dogshit for coding. So we fixed it. Meet OrcaRouter.ai DSL — the version you actually own. One prompt → fans out to any panel you want → judge + synthesizer → one god-tier answer. But unlike black-box slugs, you control the entire graph in YAML. Fable 5 level intelligence… without waiting for Anthropic to turn it back on 🧵👇

Using Verdent AI (verdent.ai) for my coding workflows and its multi-agent architecture is an absolute game-changer! 🚀 Get 40% off via my link: verdent.ai/?ref=32YIGWOr enter code on your dashboard: 32YIGW 💻✨

Analyzing Claude Fable 5. The autonomous power that handled Stripe's monthly migration in a single day is no hyperbole. 1M context and proactive reasoning are shifting software economics. Despite recent limits, the agentic era is here. #AI #Tech #ClaudeFable5 #Software

Stop asking AI coding agents to “make it beautiful.” That prompt produces template soup. Better workflow: 1. Generate an AIGC design mockup. 2. Feed the image back into Verdent. 3. Ask it to rebuild the page from the reference. Images turn taste into constraints. That’s when the agent stops guessing.

@satyanadella AI success will hinge on ecosystems, not frontier models. A future where a few models eat everything undermines industry value. We can offload tasks, but never our learning. Without human direction and judgment, compute just runs in circles.

@DavidSacks An important perspective on the balance between commercial momentum and safety accountability. The real test of an AI safety ethos is how crises are managed when guardrails are tested. Finding common ground quickly is vital for the stability of the entire ecosystem.

I’ve had a number of conversations with folks inside and outside government about the current situation with Anthropic, and here is what I believe to be true: — As we know, Anthropic publicly released its Mythos class models earlier this week under the commercial name Fable. — Fable is Mythos with guardrails. But if those guardrails fail, then you’ve exposed Mythos and its advanced cyber capabilities to people who shouldn’t have them. (Keep in mind that Anthropic itself widely promoted the idea that Mythos was a cyberweapon and needed to be regulated as such. They asked for government regulation of Mythos and championed the guardrails on Fable. If there is a vulnerability — big or small — it is Anthropic’s responsibility to patch.) — A highly credible trusted partner of both Anthropic and the USG who was testing Fable came forward with a jailbreak of those guardrails. The Admin asked Dario to fix the jailbreak or de-deploy the model. Dario refused. — In their blog post, Anthropic defended its decision by saying the jailbreak isn’t serious. That is not what the trusted partner and the USG believe; nor is that kind of minimizing language consistent with Anthropic’s brand as the AI safety company. It’s difficult to fathom how they could claim a jailbreak allowing operability of a cyber weapon could be defined as not “serious.” — In the past, Anthropic has always said that safety must be top priority and taken super seriously. In this case, Anthropic prioritized the continued offering of the consumer model over safety. — In reaction, the Admin issued the export control. The Admin did this reluctantly. It’s been very surprised that Anthropic hasn’t wanted to cooperate with a reasonable safety request (ie fixing the jailbreak issue). Anthropic’s reaction is very much at odds with their branding and ethos as a safe AI research community. — The Admin’s hope now is that Anthropic remediates the safety issue, the export control is lifted, and Fable goes back into general release. The Admin wants all of this to happen as soon as possible. It is frankly bewildered that Anthropic hasn’t wanted to comply with safety requests that it previously said were its highest priority. — Those trying to misdirect and tie this action to the prior DoW/Anthropic issues are wrong. The Admin values Anthropic’s technical capabilities and feels that this issue, while serious, should be easily resolved. The ball is in Anthropic’s court.

Built inside Verdent: 1. Upload your photo 2. Pick your World Cup team 3. Generate a football hero portrait with GPT Image 2 4. Generate a 3×3 action storyboard 5. Turn it into video with Seedance 2.0

Qwen3.7-Plus from @alibaba_cloud just landed in Verdent. Built for multimodal agent workflows, it brings strong visual understanding, coding, tool use, and software-building capabilities into the Verdent building experience. Bring an idea, a UI reference, or a rough product direction. Verdent now gives you one more powerful model to build with. Qwen3.7-Plus is free to use in Verdent for the next 7 days. Try it in Verdent today.

Verdent 2.4.0 is here. This release is about making the workspace easier to understand the moment you open it. We refined the Manager and Project pages so tasks, projects, and product work feel more organized and easier to move through. You can scan what is happening, find the area you need, and keep building with less friction. Design Mode makes the product-building flow clearer too: shape the product visually first, then turn that direction into code.

POV: you coded your own little 3D home decorator instead of just scrolling Pinterest for “room inspo” again. Drag furniture, recolor it, save layouts, then walk around the room in preview mode. 🛋️✨

The one many builders have been asking about is now in Verdent. This update is built for complex software work, deeper reasoning, and multi-step tasks that need more planning before execution. For larger codebases, long documents, and extended project histories, there is also a 1M-context option. Available in Verdent today.

A faster model option just landed in Verdent. Built for responsive coding, debugging, real-time generation, automated workflows, and multi-agent tasks, this update helps you move through everyday builds with less waiting. For larger projects and longer sessions, there is also a 1M-context option to keep more of your work in view. Try it in Verdent today.

A new long-context coding model just landed in Verdent. Built for big-codebase work, it can reason across large repos, long design docs, and image inputs in one session. Great when the task is too broad for a narrow prompt and needs deeper project context from the start. Try it in Verdent today.

A faster coding model just landed in Verdent. It brings stronger coding, reasoning, multimodal understanding, and tool use into a smaller model that feels much snappier for daily work. Great for bug fixes, small refactors, test writing, and scoped sub-agent tasks inside longer runs. Try it in Verdent today.

Calendars are usually for meetings. Memory Doors makes them portals: upload a photo, write one line, and turn each day into a cute little door back into your life. Built with Verdent.

@verdent_ai Wow! 🤯 What on earth is this, it turned out absolutely amazing! 🔥

Your travel photos can be more than static memories. This turns them into draggable animated ticket stubs: move the frame, reveal the illustrated version inside. Built with Verdent. #Verdent #AICoding #BuildinPublic #vibecoding #sideproject #webdev #aivideo

What does water look like to an AI? Not a photo. Not a physics sim. More like a memory of motion: ink, ripples, pressure, light, noise. I asked Verdent to turn “the feeling of water” into code. It built it in p5.js. Maybe prompts aren't instructions anymore. Maybe they're materials.