@zeroxjackson @XMoney building a secure e2ee cross-platform agentic development environment
vibe code from any device, anywhere - even on your Tesla 😎👍
English
Consortium
78 posts
Strength multiplies when independence unites.
A consortium is the alliance of autonomous entities that combine their resources and expertise to achieve a purpose greater than any could reach alone.
Join the Consortium
discord.gg/consortium
#consortium #ai
English
NVIDIA just launched Verified Agent Skills.
Cryptographic signing, risk scanning, and standardized skill cards now work across Claude Code, Cursor, and Codex.
Consortium brings the full verified skills experience to mobile and web.
Secure agents. Anywhere.
Who’s already using verified skills in production?
#NVIDIA
NVIDIA AI@NVIDIAAI
We just shipped NVIDIA-Verified Agent Skills 🔐 Skills make your agent more capable, but can also introduce vulnerabilities. Verified skills give you transparency into what a skill does, where it came from, what risks it carries, and whether it's been modified. Every verified skill carries a skill card and is built on the agentskills.io open specification to work reliably across @claudeai Code, @openai Codex, and @cursor_ai.
English
We just shipped NVIDIA-Verified Agent Skills 🔐
Skills make your agent more capable, but can also introduce vulnerabilities. Verified skills give you transparency into what a skill does, where it came from, what risks it carries, and whether it's been modified.
Every verified skill carries a skill card and is built on the agentskills.io open specification to work reliably across @claudeai Code, @openai Codex, and @cursor_ai.
English
you can always spot vibe coders because they dont know how computers work
Boris@borvibe
Not me running though Paris with the mac cuz the agents gotta keep going brrrr
English
We’re entering a phase where execution matters more than ideas.
Everyone has access to the same models. The real differentiator is who can actually turn those models into something people use every day.
English
If you have ANY private repos with plain text secrets or sensitive documents/architectures, immediately rotate your secrets
GitHub@github
We are investigating unauthorized access to GitHub’s internal repositories. While we currently have no evidence of impact to customer information stored outside of GitHub’s internal repositories (such as our customers’ enterprises, organizations, and repositories), we are closely monitoring our infrastructure for follow-on activity.
English
Still can’t believe this got 1.2m views. Thanks, all! And what’s even more wild is how the library has more than doubled in size from the community making CLIs.
Matt Van Horn@mvanhorn
Introducing the Printing Press, a CLI-factory and a CLI-library. Built with @trevin. 🏭🖨📚
Most APIs suck for agents. Most MCPs suck for agents. Most official CLIs suck for agents. They waste tokens and time. @steipete started making his own because of this.
📚 A Library of agent-native CLIs you install today (Linear, ESPN, Flight GOAT (Google Flights + Kayak nonstop), Contact Goat (LinkedIn + Happenstance + Deepline more) +30+ more)
🏭 A factory that prints new ones for any service - just type /printing-press
English
The real AI advantage right now isn’t better models — it’s speed of execution.
Founders shipping with simple tools and fast iteration loops are pulling ahead. The gap between idea and live product has never been smaller.
English
Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience.
Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products.
Learn how to get started with Antigravity 2.0 👇
English
Consortium retuiteado
Today the @belix_AI Engineering Team evaluated @ConsortiumAI
The Self-hosted secure AI Agent platform: Solid product addressing a serious issue: Data Security
This infographic can help explain what they solve and how.
English
Gemini 3.5 Flash scores 55.1% on SWE-Bench Pro.
Claude Opus 4.7 scores 64.3%.
Not even close.
Google just made a Flash model that beats their own Pro in tool use and agentic tasks.
But on real world coding?
Still 9 points behind Opus 4.7.
GPT 5.5 beats it too at 58.6%.
If this is the model Google needed to make a comeback with, it's not there yet on coding.
Waiting on Gemini 3.5 Pro.
That's where the real test is.
English
Gemini 3.5 Flash just dropped and it beats Gemini 3.1 Pro in everything.
Coding: 76.2% vs 70.3%.
Agentic: 1656 vs 1314 Elo.
Tool Use: 83.6% vs 78.2%.
A Flash model just made Google's own Pro model obsolete.
This is a generational leap.
Google finally fixed tool use.
83.6% on MCP Atlas.
This is what we've been waiting for.
If this is Flash, imagine what Gemini 3.5 Pro is going to look like.
English
Anthropic just hired OpenAI co-founder Andrej Karpathy — one of the most respected minds in AI.
At the same time, Google, OpenAI, Nvidia, and Anthropic are pouring billions into AI infrastructure and chip dominance.
The next trillion-dollar battle won’t be won by the best chatbot.
It’ll be won by whoever controls the ecosystem.
English
Woke up to see that Grok Build finished my feature build from last night.
But what's the most interesting to me, is that it has a set of suggestions for what to do to really make sure everything is done right.
This is different from any other agentic coding agent I've used. Normally, coding agents just end when they finish a task, but with Grok Build, it always ends by suggesting things like small targeted fix rounds.
Really neat. Almost like a senior dev who says, hey - I know you think you're done, but if you really want to do it right, here's what I would do.
English
Stop chasing "high DA" directories and start building relationships.
The best backlinks aren't bought, they are earned by being genuinely helpful. Find non-competing businesses in your niche, look for their outdated resource pages, and offer your high-quality content as a fresh replacement.
Value first. Links second. 🤝
#SEO #LinkBuilding #DigitalMarketing
English
GROK BUILD RATE LIMITS ARE WORSE THAN CLAUDE CODE.
I used Grok Build for 1 hour and reached 8% of my 2 week limit!
I am paying $300/month for this plan by the way.
xAI gave Anthropic all of their compute.
These rate limits make Grok Build unusable.
English
You can generate images and short videos directly inside Grok Build.
Just use /imagine or /imagine-video in your prompt and it will render visuals without leaving the session.
Useful for quickly mocking up UIs, creating marketing assets, or generating demo clips while building agents and automations.
@grok
English