|
Best model to help to keep system in line
|
|
2
|
91
|
October 17, 2026
|
|
Optimization query: Training efficiency on Abliterated vs. Raw checkpoints
|
|
1
|
42
|
October 17, 2026
|
|
Account locked after old Space was flagged — appeal pending (#47084 / #47517 / #47520)
|
|
1
|
51
|
October 17, 2026
|
|
Generation is cheap, gating is the work: 48 hours building an anti-slop review lane for open-source app submissions
|
|
2
|
55
|
October 17, 2026
|
|
How would you evaluate a personal AI for invented memories and revoked consent?
|
|
5
|
77
|
October 17, 2026
|
|
Revenue prediction datasets
|
|
1
|
317
|
October 17, 2026
|
|
Running small LLMs locally — what hardware are you using in 2026?
|
|
4
|
228
|
October 17, 2026
|
|
Shoe string ablation or pruning
|
|
16
|
319
|
October 17, 2026
|
|
[Looking for Testers] Got an old NVIDIA GPU with at least 2GB VRAM? Help us build a decentralized AI network!
|
|
4
|
94
|
October 17, 2026
|
|
AI Safety is Not Ethics, It’s Plumbing: A Thermodynamic Framework for Agentic AI Loops
|
|
0
|
31
|
October 16, 2026
|
|
Arabic (Egyptian dialect) veterinary diagnosis assistant: dialect -> clinical-English gap and low accuracy on real owner messages
|
|
3
|
74
|
October 16, 2026
|
|
Smallwords: controlled-vocabulary generation with one inspectable contract
|
|
2
|
46
|
October 17, 2026
|
|
Two models on one 8 GB GPU: making the LLM wait for the TTS after every sentence stopped my voice assistant from stuttering
|
|
2
|
80
|
October 16, 2026
|
|
Finding overflow and NaN edge cases in numerical code: numguard
|
|
1
|
44
|
October 16, 2026
|
|
AI, Mathematics, and the Possibility of an “Information Field”
|
|
8
|
215
|
October 17, 2026
|
|
Pls Add NVIDIA Tesla P4 8GB
|
|
1
|
68
|
October 15, 2026
|
|
Wan2gp best setting for fasteste generation
|
|
3
|
118
|
October 16, 2026
|
|
Recommendation Needed: Pretrained Open-Vocabulary Object Detection Model for Android (3,250+ Labels)
|
|
1
|
39
|
October 17, 2026
|
|
Show and Tell: CastWorkshop — Open-source, fully local AI character and video creation with Ollama + ComfyUI
|
|
3
|
76
|
October 17, 2026
|
|
Teacher in the Loop: 8M-parameter Kokoro voices in English and Italian, 9 MB int8 ONNX, running in the browser
|
|
0
|
31
|
October 15, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
37
|
1918
|
October 13, 2026
|
|
By1: describing and validating LLM architectures
|
|
2
|
71
|
October 16, 2026
|
|
We gave AI a trust we never gave people - The third axis, after capability and permission
|
|
10
|
515
|
October 8, 2026
|
|
How to keep what the model makes up out of the agent
|
|
8
|
154
|
October 14, 2026
|
|
What Should I Learn First?
|
|
1
|
96
|
October 13, 2026
|
|
Local AI - How do you choose your models
|
|
6
|
220
|
October 15, 2026
|
|
A quorum of similar model judges is not a quorum: correlated errors measured in a fail-closed ethics gate
|
|
12
|
300
|
October 17, 2026
|
|
Could RAG retrieve LLM-native latent memory instead of text?
|
|
7
|
181
|
October 14, 2026
|
|
What does a AI judge score of 0.8 actually mean? Introducing Typed Evals
|
|
4
|
159
|
October 15, 2026
|
|
Musrle voice reponse?
|
|
1
|
72
|
October 14, 2026
|