I built a whole game where every character is powered by DeepSeek V4.1 Flash on Wally.
No dialogue trees, no scripted lines. Walk up to anyone in town, say whatever you want, and they talk back in their own voice.
So I hooked up DeepSeek V4.1 Flash on Wally to a browser agent.
It browses Amazon for me, finds the best option, and adds it to my cart. Browser agents have always felt clunky because the models behind them were too slow for the job. When the model is this fast, the whole
Here's the walkthrough — 2 minutes
DigitalOcean droplet → Hermes → DeepSeek, self-hosted in a few clicks. Receipts: scripting, voicing, and rendering this exact video burned ~$0.18 of DeepSeek credits. Stop renting the dealer, buy the engine.
This "does not feel right yet" is something that happens when I'm building the mental model of the thing I'm trying to understand
Today, this takes too much time compared to how fast the code gets generated I'm trying to have mental models on demand, here's an example from
You have reached the end of the archive
All of deepseek