|
Why AI agents can change behavior without a code change
|
|
2
|
41
|
November 19, 2026
|
|
Reviewing agent-written fixes without trusting a single model
|
|
4
|
75
|
November 18, 2026
|
|
How internal AI assistants leak data through permissions
|
|
2
|
39
|
November 18, 2026
|
|
Unable to subscribe to Hugging Face PRO - "A processing error occurred"
|
|
1
|
37
|
November 18, 2026
|
|
Need advice on building a chatbot
|
|
8
|
205
|
November 19, 2026
|
|
SO-101 sim-to-real, how much the real camera pose matters for a GR00T N1.6 checkpoint
|
|
0
|
22
|
November 18, 2026
|
|
Dated-break eval: do coding models write code that stops working on a known date?
|
|
3
|
54
|
November 18, 2026
|
|
Best AI WebUi to interact with local LLM AI
|
|
3
|
190
|
November 18, 2026
|
|
Architectural Gravity – Cross-Model Agent Control Language
|
|
6
|
64
|
November 18, 2026
|
|
Need advice on choosing model to use as movies and tv shows translator after fine-tuning on my dataset
|
|
3
|
65
|
November 19, 2026
|
|
Gradio Spaces stuck in NO_APP_FILE despite valid app.py and README.md
|
|
0
|
31
|
November 18, 2026
|
|
Model-Native Structural Representation (MNSR)
|
|
1
|
58
|
November 18, 2026
|
|
Can’t Listen to a Voice Note? Turn It into Editable Text with Whisper
|
|
0
|
23
|
November 18, 2026
|
|
Agentic AI Test Checklist 110: open CC-BY-4.0 dataset of 110 test procedures for tool-using LLM agents
|
|
11
|
230
|
November 19, 2026
|
|
GPT-Rankings: a public directory of 150 GPT API gateways — feedback on reproducible evaluations
|
|
2
|
51
|
November 18, 2026
|
|
King and queen vs. a lone king: 5 small LLMs mated 3 times in 139 games, and lost the queen faster than a random mover
|
|
3
|
75
|
November 17, 2026
|
|
Running 176B Qwen3.8-Flash-Next and 284B DeepSeek-V4 on 32GB/64GB CPU RAM (0 GPUs) with llama-modchip v3.0
|
|
0
|
40
|
November 18, 2026
|
|
We gave AI a trust we never gave people - The third axis, after capability and permission
|
|
47
|
1193
|
November 19, 2026
|
|
Dual AMD GPU setup
|
|
3
|
85
|
November 16, 2026
|
|
aiFetchly: an open-source, local-first desktop AI agent for business automation
|
|
2
|
45
|
November 18, 2026
|
|
Local LLM generation on a consumer GPU: layer-streamed Qwen3.5 inference
|
|
0
|
38
|
November 17, 2026
|
|
The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They're Wrong
|
|
52
|
701
|
November 19, 2026
|
|
I built a zero-Python local LLM inference server in Java 25 (Panama FFM + CUDA/FlashInfer/Marlin + ONNX GenAI): running Qwen3.8-27B-FP8 on one 40GB GPU down to 0.3B-3.8B models on CPU/NPU
|
|
0
|
43
|
November 17, 2026
|
|
Weight training samples
|
|
0
|
32
|
November 17, 2026
|
|
Werkbank: 40 tasks for testing local LLMs with tools
|
|
4
|
92
|
November 19, 2026
|
|
Using Local LLMs for fact+claim data structuring for Knowledge Graph building
|
|
2
|
66
|
November 17, 2026
|
|
Llamatron — a 59 GB Nemotron checkpoint, republished at 18,725,978,368 bytes
|
|
2
|
48
|
November 18, 2026
|
|
Accelerate 1.15.0 — warning_once keeps adapter instances alive (measured)
|
|
2
|
37
|
November 18, 2026
|
|
The AI safety question may be backwards
|
|
8
|
186
|
November 15, 2026
|
|
Agentmetry: an open-source record of what your coding agent did on your machine Category: Show and Tell
|
|
15
|
192
|
November 19, 2026
|