|
About the AI-Feeds category
|
|
0
|
11
|
August 9, 2025
|
|
The Full Story of the “Distillation Storm” Among China’s Large-Model Companies
|
|
0
|
5
|
July 27, 2026
|
|
How do you make a good nsfw image prompt?
|
|
0
|
4
|
July 27, 2026
|
|
I built an open source self hosted version of OpenRouter called Millwright, would love any feedback
|
|
0
|
5
|
July 27, 2026
|
|
Local AI for game dev tooling, am I doing this wrong? (16GB & 24GB VRAM)
|
|
0
|
4
|
July 27, 2026
|
|
In Lm studio , how do you stop a model unloading from vram?
|
|
0
|
4
|
July 27, 2026
|
|
Pitching a midnight deepthought
|
|
0
|
4
|
July 27, 2026
|
|
Oops! Some AI-forward companies realize they need humans after all, and are re-hiring fired workers
|
|
0
|
4
|
July 27, 2026
|
|
Combining 7800XT with 7900XTX
|
|
0
|
5
|
July 27, 2026
|
|
OpenAI management decided earlier today not to join the "Open Secure AI Alliance", founded by Nvidia CEO Jensen Huang. The decision was shared internally and reportedly met with backlash from employees
|
|
0
|
2
|
July 27, 2026
|
|
Im 11, built a fully local AI coding assistant that beats Llama 4 Scout on HumanEval — no API keys, no internet
|
|
0
|
2
|
July 27, 2026
|
|
The Problem with Private Safety Stacks in Government AI
|
|
0
|
0
|
July 27, 2026
|
|
Trying to learn how to run local ai for coding, and so is this guy apparently
|
|
0
|
1
|
July 27, 2026
|
|
What am I missing? Self-Hosting Kimi K3 has 34× First-Year ROI at 90%
|
|
0
|
0
|
July 27, 2026
|
|
Running Gemma 2B locally on iPhone for offline calendar actions (~516 MB active RAM, 21.6 tok/s, GGUF weights)
|
|
0
|
0
|
July 27, 2026
|
|
MirrorCode: Opus 4.7 reimplemented a program from CLI access alone — 14h, $251, vs an estimated 2–17 weeks for a human
|
|
0
|
1
|
July 27, 2026
|
|
I built a public JARVIS-style AI infrastructure scaffold you can clone locally or connect to GitHub + Supabase
|
|
0
|
0
|
July 27, 2026
|
|
[Project] Local LLM agent playing Perfect Dark on Mac — real locomotion + combat (on-device MLX)
|
|
0
|
0
|
July 27, 2026
|
|
Is anyone hosting a private chatgpt using open weights models for friends and family?
|
|
0
|
4
|
July 27, 2026
|
|
Pair of NVIDIA DGX Spark AI Supercomputers | 256GB Total RAM Cluster Bundle
|
|
0
|
0
|
July 27, 2026
|
|
I built a deep learning library from scratch in C that lets you train language models
|
|
0
|
0
|
July 27, 2026
|
|
What’s the minimum context window you’d use for coding agents?
|
|
0
|
0
|
July 27, 2026
|
|
Please support me
|
|
0
|
0
|
July 27, 2026
|
|
Council 1.2: drop any AI's answer into a blind review by every other model you have
|
|
0
|
1
|
July 27, 2026
|
|
Council 1.2: drop any AI's answer into a blind review by every other model you have
|
|
0
|
0
|
July 27, 2026
|
|
How to properly use 2xH200
|
|
0
|
0
|
July 27, 2026
|
|
A political compass for AI where anyone can add their stance
|
|
0
|
1
|
July 27, 2026
|
|
Gemma vs Qwen vs GLM vs Llama?
|
|
0
|
1
|
July 27, 2026
|
|
Tool-call accuracy fell off at ~9k tokens on a model whose context window is 16k and memory could have held 53k
|
|
0
|
0
|
July 27, 2026
|
|
I was looking for a light weight web application for RP, couldn't find a good and easy, so built one myself - NanoRP
|
|
0
|
1
|
July 27, 2026
|