Gemini 3.7 Flash now also powers Spark! I think... Spark is massively underrated for tons of work tasks, and 3.7 Flash means it now has better tool calling and really high success at multi-step, multi-skill workflows. These 10 prompts are my go-to for automating the weekly grind:show more

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 for hooking them up!show more

Gemini 3.6 Flash is available in Antigravity CLI ☄️... Set it via /model which also now has an effort level slider! Recommend using medium effort for most tasks. Give it a try and let us know what you think. 🙏show more

You can now use GPT 5.5, Gemini 3.7 Flash,... Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.show more

Step 3.7 Flash is one of the fastest low-cost... open models, now live in Command Code. • 400 tokens/sec 🍃 • 256K context window • 3 reasoning levels Sharp instruction-following and strong /design taste. $1 Go plan with 10x free usage credits, best way to try it.show more

Qwen just released Qwen-Image-2.1, and this is exactly why... open models matter. I loaded it onto my NVIDIA DGX Spark and built Spark Image Lab, a local image generation and editing workspace designed for the DGX Spark ecosystem. QWEN-IMAGE-2.1 • Text-to-image generation • Image editing • Native transparent/RGBA workflows • Up to 10 reference images • Strong identity and product preservation • Improved typography, lighting, textures and detail SPARK IMAGE LAB • Clean Gradio interface • Width and height controls • Steps, seed and batch controls • Persistent generation history • Prompts and settings saved with every result • Reference images saved and restored • Docker setup for DGX Spark • Measured DGX Spark performance benchmarks Everything runs locally. Spark Image Lab is now open source under the MIT License. This is the first public alpha, so clone it, test it on your DGX Spark, open an issue and show me what you create. MODEL REPOshow more

Most agentic workflows die a slow death from cost... creep before they ever finish the job. SenseTime's new Token Plan flips that: complex multi-step tasks now run at ~60% lower token cost, and for the first month you get 1,500 calls refreshing every 5 hours — free. That's enough room to actually stress-test long-chain workflows instead of babysitting your token meter. Try it →show more

Newburgh, New York Walmart has all their lights flashing.... This has been happening all over the country, it also just happened at Asheville, North Carolina airport Is this due to the “Drones/ Orbs?” Are they testing our infrastructure for some upcoming event? “The lights do not always flash. I go to Walmart all the time and they never flash like this”show more

🚨Gemini 3.6 Flash is trash I tested it on... a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?show more

Multi-robot learning is getting a serious boost! 📚 Researchers... have extended Isaac Lab to train heterogeneous multi-agent robotic policies at scale. The new framework supports high-resolution physics, GPU-accelerated simulation, and both homogeneous and heterogeneous agents working together on coordination tasks. They benchmarked different approaches (MAPPO: Multi-Agent Proximal Policy Optimization and HAPPO: Heterogeneous Agent PPO) across six challenging scenarios and showed that large-scale multi-robot training is not only feasible, but efficient. It’s an important step for real-world robotic collaboration, where teams of robots need to coordinate, split tasks, adapt roles, and interact dynamically, not just operate as identical clones. The code is open-source, and it pushes Isaac Lab closer to what robotics actually needs: scalable, physics-driven environments where many different robots can learn to work together. Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →show more

Muse Spark 1.3 is now in Codex!! OpenCode's free... tier runs it for nothing, and $10 on OpenCode Go gets you over 45,300 requests. It's basically Opus 5 tier too. There's a catch though. Meta may use your inputs and outputs for training, which is the whole reason the tier is called contributor and the whole reason it's free. Muse 1.3 just sits in the picker next to my paid models now. I'll just use Astra + Muse Spark for subagents. Gonna keep everything in stock in case we need it.show more

We are entering an extremely exciting era for open-weight... models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.show more

Anthropic dropped 33 pages for Claude trading bots Last... night I decided to try writing one and it worked out for me In 10 hours this script made me $561 The bot has a win rate of about 71% Wallet: Copytrade: Here is the full strategy: The system builds automated workflows for Claude by packaging domain expertise into structured skills that activate automatically when relevant tasks appear Skill architecture Each skill is structured as a modular package containing instructions, scripts, and reference materials This allows Claude to apply specialized workflows without requiring the user to repeat instructions in every conversation Progressive context loading Skills follow a three-layer architecture where only minimal metadata is loaded initially Full instructions and supporting files are accessed only when needed, reducing token usage while maintaining specialized expertise Trigger detection Skills activate when the user request matches defined trigger phrases or workflows This ensures the correct workflow loads automatically without requiring manual prompting Workflow execution Once activated, the skill executes a predefined multi-step process These workflows can include data analysis, document generation, automation scripts, or coordination across external tools Consistency and reliability Because workflows are encoded directly in the skill instructions, Claude performs tasks using consistent methodology rather than ad-hoc prompting Testing and iteration Skills are continuously refined through triggering tests, functional validation, and performance comparisons to ensure reliable execution Automation edge Instead of solving tasks from scratch each time, the system repeatedly applies optimized workflows Over time this dramatically reduces prompt complexity, improves output consistency, and scales productivity across thousands of tasksshow more

Woow Google has just rolled out the AI model... Flash Thinking 2.0 This is the first reasoning model capable of accessing YouTube and it changes everything: - Search for a video on your topic - Ask Gemini to think about the video - You'll have a tailor-made result in 10 sec. And it's even connected to Google Search and Maps!show more

holy sh*t. this is f**king insane. muse spark 1.3... beats fable 5 and gpt 5.6 at 1/20th price i cancelled my $200/mo Claude subscription for this. i replaced fable 5 with muse spark 1.3 for only $10/mo on opencode go [it takes 3 minutes to set up:] 1/ install the model-router repo 2/ toggle opencode free to green 3/ that’s it.show more

DeepSeek v4.1 Flash might actually be good enough for... the majority of my work. I’m spending $300/month across two Codex accounts and still constantly worrying about limits. Meanwhile, I’ve had 5+ agents running on DeepSeek all day and I’ve used 15% of my weekly allowance. $10/month (OpenCode) vs. $300/month. At some point, “good enough and available” beats “better, but you can’t use it.”show more

Chronicles Of The Kid is out now. I couldn’t... be more proud of this album. There are people who share my experiences and also walk this earth contemplating what it means to be human. For them, and others like them, I dedicate this record. 🖤show more

After a few more hours, I think I've figured... out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.show more

Claude can make your own money printer That is... exactly what happened to me I wrote my own script It took me 6 hours On the very first night the bot made $2,705 profit Copytrade: Wallet: Here is the full strategy: The system builds automated workflows for Claude by packaging domain expertise into structured skills that activate automatically when relevant tasks appear Skill architecture Each skill is structured as a modular package containing instructions scripts and reference materials This allows Claude to apply specialized workflows without requiring the user to repeat instructions in every conversation Progressive context loading Skills follow a three layer architecture where only minimal metadata is loaded initially Full instructions and supporting files are accessed only when needed reducing token usage while maintaining specialized expertise Trigger detection Skills activate when the user request matches defined trigger phrases or workflows This ensures the correct workflow loads automatically without requiring manual prompting Workflow execution Once activated the skill executes a predefined multi step process These workflows can include data analysis document generation automation scripts or coordination across external tools Consistency and reliability Because workflows are encoded directly in the skill instructions Claude performs tasks using consistent methodology rather than ad hoc prompting Testing and iteration Skills are continuously refined through triggering tests functional validation and performance comparisons to ensure reliable execution Automation edge Instead of solving tasks from scratch each time the system repeatedly applies optimized workflows Over time this dramatically reduces prompt complexity improves output consistency and scales productivity across thousands of tasksshow more