JD Workshop

@CommandCodeAI This gonna be good

Yes $1 Go plan is cool. But more is coming. Noon 12pm Monday, 1st June. Command Code deal drop. This one is gonna be crazy good!!

Just want to make this clear: We didn't make Hermes Agent to be a "starts with nothing, you work it all out" agent. This is not the minimalist, start from nothing, agent. We want Hermes to work out of the box for most people. So you aren't spending weeks just getting the agent to work, or have the capabilities you need. This means that yes, there are more built in things then something like nanoclaw or pi, which start with nothing, and you just have to figure it out. That is an intentional design decision. You can from the modest baseline that has capabilities that are likely broader than you need, but not egregious, take it from there if you want to tinker with it. Run `hermes skills config` or `hermes tools` to disable whatever you want. We even have a way to upload your whole "Agent" as a github repo, so you can install hermes fresh with your exact setup again later or share them. We have a massive interface for extensions so you can tinker with it to infinity. But if you don't want to become an agent engineer - with Hermes, you don't have to.

@PhantomByteAI @Cryptor_dot @Teknium @imbabybrooklyn Do you switch models when moving to Pro for deep reasoning or skill building? Or do you just have your Flash use delegate task?

@Cryptor_dot @Teknium @imbabybrooklyn 80%+ of my work is done by DeepSeek4 Flash. I build skills using Kimi 2.6 and DeepSeek4 Pro and run them with Flash, unless the skill calls for a bigger model. However, I don't "vibe code"; instead, I tell the model exactly what I want and how to do it.

👀 forbes.com/sites/sandycar…

Step 3.7 Flash is now free for 30 days via Nous Portal It is a new MoE vision-language model focused on agent efficiency, coding, search, and multimodal workflows — and Hermes Agent users have been loving it, so thank you to @StepFun_ai for hooking them up!

@AbdMuizAdeyemo How are you providing Gemini 3 Flash to your agent? Is it from Gemini CLI OAuth?

I hit my Codex limit, so I just funded DeepSeek platform account with $2 and connected DeepSeek V4 Flash to Hermes. I still have Gemini 3 Flash from Google as another fallback. Codex for heavy work. DeepSeek and Gemini for daily momentum. The goal is simple. Never stop shipping.

OpenCode x MiMo V2.5 - Free for a limited time 1M context • reasoning • text • image

@opencode Things like this is exactly why you guys have been awesome for getting me set up with my agentic workflows!

@FloNocode @stitchbygoogle @contra It follows natural language prompts better and giving it reference images and websites also gives better and more accurate results now.

@jdworkshop_ @stitchbygoogle @contra Hi, can you share the result please because i have another opinion for website ? Can you detail where you see major differences ?

The Stitch Challenge is coming! $10K in total prizes. May 27th. Fueled by the good folks @contra

@HermesAgentTips Looks like it was taken off today

Deepseek V4 Flash is currently free on Hermes agent Nous portal.. whos enjoying Deekseek V4 Flash so far?

We heard concerns that Antigravity consumes many tokens for simple tasks now. So, we're adding Gemini 3.5 Flash (Low) as a way to optimize token usage for these tasks. In our internal testing, it generates around 45% fewer tokens than Gemini 3.5 Flash (Medium) and generally outperforms Gemini 3 Flash (High) on SWE tasks. We've also gone ahead and reset Gemini quota across all paid plans to make sure you have all the tokens needed to build for the next week 🙂

@Google Gemini Spark is for both tiers or just Ultra? Quite confusing info there

We’re launching a new $100/month AI Ultra plan, specifically tailored for developers, technical leads, knowledge workers and advanced creators. We’re also reducing the monthly price of our top-tier AI Ultra plan from $250 to $200. Both tiers grant access to some of our most advanced features, including: -Gemini Spark, our new 24/7 AI agent, will roll out to trusted testers this week, and we’re planning to roll it out as a Beta for Google AI Ultra subscribers in the U.S. next week. -Project Genie, our experimental research prototype that is rolling out to all eligible AI Ultra $200 subscribers

Our Google AI subscriptions offer higher limits in the Gemini app, extra storage, and premium benefits across Google. Yesterday at #GoogleIO, we announced even more benefits at no extra cost. See what’s new — and find which one is right for you 🧵⬇️

@sama 1. Health 2. Human Connections

what problem do you most hope AI will solve in the future? maybe we can help!

@GeminiApp @OpenTable @canva @Instacart

Gemini can now connect to even more apps, including @OpenTable, @Canva, and @Instacart. Whether you're booking a table at a restaurant, creating a flyer, or ordering groceries, Gemini doesn’t just find info, it helps you take action seamlessly with connected apps.

@Google dropping that "One click export to Antigravity from @GoogleAIStudio" line casually at the end like it's not a game changer 👀

@NewsFromGoogle @antigravity @Google dropping that "One click export to Antigravity from @GoogleAIStudio" line casually at the end like it's not a game changer 👀

The Google @Antigravity ecosystem is officially expanding. We're giving you total control over how you build with AI agents. Whether you're a solo developer or an enterprise team — here’s what’s new in Antigravity: 🔹 Antigravity Agent 🔹 Antigravity SDK 🔹 Antigravity CLI 🔹 Native @Android dev support 🔹 @GoogleCloud integration 🔹 Antigravity 2.0 Desktop app 🔹 One click export to Antigravity from @GoogleAIStudio #GoogleIO

Gemini 3.5 Flash is amazing! - Performs better than 3.1 Pro on coding & agentic tasks - 4x faster than other frontier models - 12x faster in @antigravity - 800 tokens/sec! - Often at less than half the cost And Pro to come… Try it in @antigravity, @GeminiApp & more - enjoy!

This completely shatters my old "Pro for reasoning, Flash for speed" playbook. It's insane how fast and powerful this is, especially inside Antigravity. Am I missing something here, or did Google just render 3.1 Pro obsolete with its very own for the foreseeable future? #GoogleIO #GoogleDevelopers #GeminiAI

Meet Gemini 3.5 Flash — our strongest agentic and coding model yet. It delivers frontier-level performance at 4x the speed of comparable frontier models — often at less than half the cost. Generally available, starting today. 🧵 #GoogleIO

Gemini 3.5 Flash just dropped at Google I/O and it completely shatters my old "Pro for reasoning, Flash for speed" playbook. 4x faster than comparable frontier models—and is significantly faster in reality inside Antigravity. Really, you gotta try it yourself. 76.2% on Terminal-Bench 2.1. Better coder yet cheaper. Am I missing something here, or did Google just render 3.1 Pro obsolete with its very own for the foreseeable future? #GoogleIO #GoogleDevelopers #GeminiAI

@Google @mweinbach Gemini on top!?

@mweinbach Can't wait to show you everything we've been cooking

I am genuinely so excited for Google IO tomorrow