Quick start: a software factory in Cosmos is two screens and one prompt. 1. Connect your repo 2. Create an environment 3. Describe the factory you want Advisor picks the experts, writes the configs, applies them, and asks you when it needs a decision.

Has anyone tried to build self-developing apps and websites? My concept for this is that you put some feedback form on the website where the user can report bugs or request features. Then once they hit submit, an agent reads the bug report and sees if it can diagnose and fix the bug itself and open a pull request. Or respond to the user if its user error or something. You just have to merge pull requests in or give the model some more direction, but you could have an app or service that sort of evolved on its own organically based on user feedback even when the developer or maintainer was busy with other things. You could imagine the user filing bug reports and having it fixed in minutes. Filing a feature request and using it a few hours later. Who knows, maybe if the model has strong judgement someday development can just proceed fully autonomously.

We are excited to announce that we have partnered with @_inception_ai to make Mercury 2 available on Baseten. This makes us the first inference platform to bring Inception’s diffusion LLM to production. Inception’s dLLM architecture fixes the bottlenecks of sequential token generation and can deliver 1,000+ tokens/sec on standard NVIDIA GPUs. Early users like @augmentcode have seen impressive results, such as an 82% reduction in latency and 90% cost savings, while maintaining high quality.

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

So what would you say....you do here?