Johannes Haas

@0xSero I use the 20$ plan and it often happens that it says is not available for some time. Does this not happen to you?

I pay 40$/mo and have not even once ran out and I hammer it all day. Kimi is the best model in Parchi, beyond a doubt

It's crazy how bad factory.ai is compared to everything else available.

@bilawalsidhu Super exiting! Can you drop a video going through your workflow? It's so inspiring what you are building and it would be super interesting to see how you take the right decisions for implementing all those features and how you move so fast with your agentic setup.

Full WorldView walkthrough is up on the channel. Every feature, every data layer, and how I used agents to put it all together. Check it out here: youtu.be/rXvU7bPJ8n4

@agent_wrapper Nice work! How are you keeping api cost down? I assume subscriptions are throttling way too much for this amount of agents and without proper caching it will probably get quite expensive.

We just open-sourced the system we use to manage 30 parallel AI coding agents per person. 40K lines of TypeScript. 3,288 tests. 17 plugins. Built in 8 days — by the agents it orchestrates. Yes, we used Agent Orchestrator to build Agent Orchestrator. Some numbers: → 500+ agent-hours in 24 human-hours (20x leverage) → 86 of 102 PRs created by AI (84%) → After Day 4, I stopped writing code entirely Spawn agents. Step away. Ship faster.

@saranshhx What exactly do you need from supabase? You can just host a postgres db on most provider where you host your backend.

Honestly, is there any alternative to supabase ?

@OfficialLoganK @grok do I need a pro plan to use the model?

Introducing Gemini 3.1 Pro, our new SOTA model across most reasoning, coding, and stem use cases!

@JOBhakdi What tool are you currently using to code?

Vibe coding is becoming more and more perfect, if you have a small team to clean backend and devops (easy). It's crazy, we are building a whole investor management and CRM system for Pioneer Bonds within days, and it's better than anything I have ever seen in enterprise (because I designed it lol)

@signulll Anxiety is ramping up that I won't have this kind of job in some years!

i am a trained software engineer with an ml grad degree & i ask this question with genuine sincerity. if you’re a software engineer right now, how do you feel about your future?

@saranshhx @X Could me in! What are you especially interested in?

Hey @X I'm looking to #connect with people interested in : - Frontend - Backend - Full stack - DevOps - Ai/ML - Data Science - Freelancing - Startup - Tech Let's grow together 🤝🏻 Say Hi 👋 😀

@AsishSunny5 Now that I started trying to build some following on x I definitely feel that way. On the other hand I only see posts like 'What are you building right now? 👇' in my timeline

The worst part of starting on X is the "shouting into the void" phase. You create real value , but there's no one to hear it yet. I’ve been there. It feels lonely. So let’s change that. Follow, support, and lift each other up ❤️👇

@vineerpasam I am building an agent orchestration which plugs into any GitHub repo and can help you schedule tickets, plan the vision of your project etc. I'm trying to improve my own agent workflow with easier reviews etc. It's mostly for my own use to execute faster on new projects.

🚀 Hey Founders, Builders, Developers What are you building right now? Drop your product in the replies 👇 My last post reached 13,000+ people. So this is your chance to market it here.

@ssushilllltwt Good choice, I should do that as well, but it feels like a chore.

@HaasDev93 i am building my X account currently

If you are building and growing your X account let’s connect Drop your niche below I follow builders

@stevenmarkryan @grok summarize

• Elon's Cybercab Promise Causes Tesla Community To Melt Down • Tesla Skeptic About To Find Out • I Have A Confession...

@mdnlabs Are you using the official x API?

I built this. Costs me $0.07/post. It will hit 5 platforms at once.

Looking for an AI marketing agent that does more than just 'write captions.' I need something that actually manages [Social/Ads/SEO] end-to-end. What’s in your tech stack right now? 🛠️

@Voxyz_ai How much does it cost you to run? I suppose this is quite expensive if you use the apis of top tier models?

one thing i didnt cover in the article: you cant just use one model for every agent. same model and they all start sounding the same. i mix claude opus 4.5 with gpt-5.3, gemini 3 pro, each vendor has a different vibe that gives agents real personality. model diversity matters as much as prompt diversity

@zephyr_z9 @grok what's CC multiagent

Output quality: Kimi 2.5 > Opus 4.5 (Claude Code) > GPT 5.2 > Gemini 3 Pro CC's multiagent/subagent system is damn good. Format was great too, but it ranks below Kimi because it included irrelevant stuff in the output

@karpathy @grok summary?

I took delivery of a beautiful new shiny HW4 Tesla Model X today, so I immediately took it out for an FSD test drive, a bit like I used to do almost daily for 5 years. Basically... I'm amazed - it drives really, really well, smooth, confident, noticeably better than what I'm used to on HW3 (my previous car) and eons ahead of the version I remember driving up highway 280 on my first day at Tesla ~9 years ago, where I had to intervene every time the road mildly curved or sloped. (note this is v13, my car hasn't been offered the latest v14 yet) On the highway, I felt like a passenger in some super high tech Maglev train pod - the car is locked in the center of the lane while I'm looking out from Model X's higher vantage point and its panoramic front window, listening to the (incredible) sound system, or chatting with Grok. On city streets, the car casually handled a number of tricky scenarios that I remember losing sleep over just a few years ago. It negotiated incoming cars in tight lanes, it gracefully went around construction and temporarily in-lane stationary cars, it correctly timed tricky left turns with incoming traffic from both sides, it gracefully gave way to the car that went out of order in the 4-way stop sign, it found a way to squeeze into a bumper to bumper traffic to make its turn, it overtook the bus that was loading passengers but still stopped for the stop sign that was blocked by the bus, and at the end of the route it circled around a parking lot, found a spot and... parked. Basically a flawless drive. For context, I'm used to going out for a brief test drive around the neighborhood to return with 20 clips of things that could be improved. It's new for me to do just that and exactly like I used to, but come back with nothing. Perfect drive, no notes. I expect there's still more work for the team in the long march of 9s, but it's just so cool to see that we're beyond finding issues on any individual ~1 hour drive around the neighborhood, you actually have to go to the fleet and mine them. Back then, I processed the incredible promise of vehicle autonomy at scale (in the fully scaleable, vision only, end-to-end Tesla way) only intellectually, but now it is possible to feel it intuitively too if you just go out for a drive. Wait, of course surround video stream at 60Hz processed by a fully dedicated "driving brain" neural net will work, and it will be so much better and safer than a human driver. Did anyone else think otherwise? I also watched @aelluswamy 's new ICCV25 talk last week (x.com/aelluswamy/sta…) that hints at some of the recent under the hood technical components driving this progress. Sensor streams (videos, maps, kinematics, audio, ...) over long contexts (e.g. ~30 seconds) go into a big neural net, steering/acceleration comes out, optionally with visualization auxiliary data. This is the dream of the complete Software 1.0 -> Software 2.0 re-write that scales fully with data streaming from millions of cars in the fleet and the compute capacity of your chip, not some engineer's clever new DoubleParkedCarHandler C++ abstraction with undefined test-time characteristics of memory and runtime. There's a lot more hints in the video on where things are going with the emerging "robotics+AI at scale stack". World reconstructors, world simulators "dreaming" dynamics, RL, all of these components general, foundational, neural net based, how the car is really just one kind of robot... are people getting this yet? Huge congrats to the team - you're building magic objects of the future, you rock! And I love my car <3.

@interesting_aIl @grok how does the robot work?

These students were tasked with created a robot that could climb the wall in the fastest time