#text
6 条发现 · 精选自开放网络的发现，按时间从新到旧。
-
Show HN: Open-world text adventure played through AI agents
Hey HN, I am building Eremoterra, this experiment of trying to make a game out of an MCP (to learn MCP stuff, but also had a lot fun designing the game). You play in your own agent. The server returns a fact sheet for the place you are. The world is like real Earth, but empty (until the players start to arrive) and only the natural wold (as humanity never existed). The agent narrates the sheet and can write what you confirm in a sort of lore book, typed events and fixed templates, so the model cannot become the source of truth. I added some NPCs that, i hope, bring some interesting emergent be
Show HN · EN
-
Show HN: A terminal viewer for plain text data files (JSON,YAML,CSV,XML,)
When I started working hands-on with OpenAPI specifications, it became clear very quickly that using an editor to read large volumes of deeply nested JSON sucks, a very great deal. So I went looking for something to help, and came across https://jless.io This is an awesome terminal app for navigating nasty JSON documents. I am forever indebted to Paul Martinez for writing this tool. But it did have some gaps. It couldn't reload files that had changed, keeping your place in the JSON structure, which I really needed. And it only loaded one file at a time. But unfortunately it was written in Rust
Show HN · EN
-
Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)
My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation. Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. You make, you tweak, you get better. In our opinion, they're not usable yet for storytelling. When we set out to build Linum v3 (our next video model) earlier this year, the primary goal was to bring the cost envelope of inference down significantly. If our model is fast and cheap, it's the first step
Show HN · EN
-
Show HN: TextoCAD – Text to editable CAD (STEP/STL), runs locally with your key
Text to CAD: describe a part in plain English, get an editable parametric CadQuery/OpenSCAD model. Exports STEP, STL, 3MF and URDF. Runs locally with your own AI key. - harisharandangi/textocad
Show HN · EN
-
Language Models for Text Classification: From Bag-of-Words to Jev
A Visual Guide to RNNs, CNNs, Transformers, and Calibration, with Hands-On Experiments on Accuracy and Efficiency
Ahead of AI · EN