Kraggi

Unpopular flex: my secret weapon for building Nyx isn't Claude or Codex. It's Hermes Agent. Started using it ~2 months ago at 2k stars, now it's one of three agents I run in parallel every day. Works so well I added first-class support for it inside Nyx. So happy to see how much they've blown up lately, massively deserved. @NousResearch @Teknium

@gdb "Friction is starting to disappear" except every AI tool still ships a single chat window. The narrative is ahead of the UI.

The world is transitioning to a compute-powered economy. The field of software engineering is currently undergoing a renaissance, with AI having dramatically sped up software engineering even over just the past six months. AI is now on track to bring this same transformation to every other kind of work that people do with a computer. Using a computer has always been about contorting yourself to the machine. You take a goal and break it down into smaller goals. You translate intent into instructions. We are moving into a world where you no longer have to micromanage the computer. More and more, it adapts to what you want. Rather doing work with a computer, the computer does work for you. The rate, scale, and sophistication of problem solving it will do for you will be bound by the amount of compute you have access to. Friction is starting to disappear. You can try ideas faster. You can build things you would not have attempted before. Small teams can do what used to require much larger ones, and larger ones may be capable of unprecedented feats. More and more, people can turn intent into software, spreadsheets, presentations, workflows, science, and companies. People are spending less energy managing the tool and more energy focusing on what they are actually trying to create. That shift brings a kind of joy back into work that many people haven’t felt in a long time. Everyone can just build things with these tools. This is disruptive. Institutions will change, and the paths and jobs that people assumed were stable may not hold. We don’t know exactly how it will play out and we need to take mitigating downsides very seriously, as well as figuring out how to support each other as a society and world through this time. But there is something very freeing about this moment. For the first time, far more people can become who they want to become, with fewer barriers between an idea and a reality. OpenAI’s mission implies making sure that, as the tools do more, humans are the ones who set their intent and that the benefits are broadly distributed, rather than empowering just one or a small set of people. We're already seeing this in practice with ChatGPT and Codex. Nearly a billion people are using these systems every week in their personal and work lives. Token usage is growing quickly on many use-cases, as the surface of ways people are getting value from these models keeps expanding. Ten years ago, when we started OpenAI, we thought this moment might be possible. It’s happening on the earlier side, and happening in a much more interesting and empowering way for everyone than we’d anticipated (for example, we are seeing an emerging wave of entrepreneurship that we hadn’t previously been anticipating). And at the same time, we are still so early, and there is so much for everyone to define about how these systems get deployed and used in the world. The next phase will be defined by systems that can do more — reason better, use tools better, plan over longer horizons, and take more useful actions on your behalf. And there are horizons beyond, as AI starts to accelerate science and technology development, which have the potential to truly lift up quality of life for everyone. All of this is starting to happen, in small ways and large, today, and everyone can participate. I feel this shift in my own work every day, and see a roadmap to much more useful and beneficial systems. These systems can truly benefit all of humanity.

@bridgebench The model that wins isn't the one topping benchmarks. It's the one that doesn't break your agent loop at 3am. Grok still has to prove that part.

Grok 4.20 Reasoning just took #1 on the new BridgeBench Reasoning benchmark. Beating GPT 5.4 and Claude Opus 4.6. This model keeps climbing every single week. Hallucination #1. Now Reasoning #1. While Anthropic is throwing 500 errors, xAI is quietly building the most well-rounded model on the market. bridgebench.ai

@bindureddy This is why single-window IDEs are dying. Codex here, Opus there, critic, tester, judge. Five agents. One chat window can't hold this.

@DbgKinggg @NousResearch Been running Hermes in agent loops for weeks. Stability is on another level.

I love Hermes @NousResearch , much better than OpenClaw

@ZaiforStartups This is exactly why I built Nyx. More parallel paths means more agents running at once. One chat window can't hold that shape. You need a canvas.

AI won’t just replace work it will expand it as execution becomes easier teams don’t do less they explore more more attempts more parallel paths more surface area

@bridgemindai Elephant = memory. 262K context, prompt caching, free inference. This smells like a Chinese lab testing before launch. Kimi or Qwen team shipping something big next week.

A stealth 100 billion parameter model just appeared on OpenRouter. No announcement. No company name. Just "Elephant Alpha." Released today. 262K context window. $0 input. $0 output. Free. Code completion. Debugging. Agent interactions. 256K context with function calling and prompt caching. Nobody knows who built this. @bridgebench is testing it now.

@minchoi This is exactly why wrappers are dead. If your product is just a chat window on top of Claude, Anthropic will eat you alive. Desktop IDE with canvas and worktrees is a different game.

It's happening. New leak from Anthropic appears they are building a full-stack app builder inside Claude. They are coming for everything.

@ivanfioravanti Every week a new model claims to be the coding king. The only test that matters: can it hold context across a real codebase for a week straight without going off the rails?

Kimi K2.6 code preview is out! 🤩

How many agents do you run in parallel right now?

Every AI coding tool is making the same mistake. Cursor, Windsurf, Codex, Claude Code - they all give you one agent in one window. But real work isn't one task at a time. It's three agents in three worktrees solving three problems while you review the fourth. The future isn't a smarter chat window. It's a canvas.

The trick: split your work into independent tasks. Each agent gets its own worktree, its own branch, its own scope. No conflicts. No context bleeding. You just review and merge.

And no matter how smart the model gets, you still review everything yourself. That's not changing anytime soon. Worktrees let agents work in isolation. Canvas lets you see all of them at once. That's the workflow.

@iwouldusethat Thank you, the launch is not far off, and I continue to work every day without a day off.😁

@Kraggich eagerly awaiting the launch sir

Switching between projects in a terminal IDE is pain. Cmd+Tab between 5 windows, lose context, forget where you were. So I stole Discord's playbook — workspace rail on the left. Each project = its own canvas with agents, terminals, editors. Click an icon > instant switch. Everything preserved. Even auto-detects your project's favicon as the icon.

@buildinpublic building Nyx - an infinite canvas IDE. Agents, terminals, browser, editor, todos - all living side by side on one canvas. Really excited about it) getnyx.dev

What are you working on this week?

@nyxquant It happened again 🤣

@Kraggich i like it, also because it has a very cool name lol

Unpopular flex: my secret weapon for building Nyx isn't Claude or Codex. It's Hermes Agent. Started using it ~2 months ago at 2k stars, now it's one of three agents I run in parallel every day. Works so well I added first-class support for it inside Nyx. So happy to see how much they've blown up lately, massively deserved. @NousResearch @Teknium

@crypto_guro @_Chandan_17 Sure, followed!

@Kraggich @_Chandan_17 Hi, let's connect. I’ll FB ASAP

X is cool… but it hits different when you connect with people who code if you’re into tech / AI /programming, say hi 👋🏻

@WesRoth Love this concept. Actually shipped something similar in Nyx recently, a todo tile where each task can spin up its own agent. They all run in parallel on the canvas and you see every one working in real time. Cool to see OpenAI thinking the same way.

OpenAI is reportedly developing a new experimental feature for its Codex model currently dubbed "Scratchpad."

@jameslevicf Claude. Then run it inside an IDE where you actually see what it's building in real time.

Lovable or Claude?

@LLMJunky Built-in browser and element comments, sounds familiar. Nyx has had this since day one. Browser tile on the canvas, inspect any element, screenshot it, send it straight to an agent. Nice to see Codex catching up.

@eyupyusufa Practical workflows over theory. This is what people actually need. Curious how many of these translate to multi-agent setups where you run different workflows in parallel.

OpenAI yeni bir Codex Use Cases sayfası yayınladı. Açıkçası son zamanlarda gördüğüm en pratik AI kaynağı olmuş. 24 workflow var: ✅ Her senaryo komple bir workflow: prompt, spec, plugin, skill ✅ Sadece kod değil: slayt, onboarding, analiz vb de var ✅ iOS/macOS kategorisi: Liquid Glass, SwiftUI refactoring, Simulator debug ✅ Workflow'ları skill olarak kaydedip tekrar kullanabiliyorsunuz