|
What if a small LLM didn't have to make every decision?
|
|
3
|
75
|
September 23, 2026
|
|
How much VRAM do you realistically need to fine-tune small models on a laptop?
|
|
1
|
42
|
September 24, 2026
|
|
Learning about recursive self-improvement — looking for feedback on my experimental framework
|
|
3
|
59
|
September 23, 2026
|
|
Trying to improve output speed with MLX models on LM Studio
|
|
1
|
42
|
September 23, 2026
|
|
What do you think about AI?
|
|
14
|
420
|
September 21, 2026
|
|
SplitMOE- similar to deepseek-MOE `same same but different`
|
|
2
|
93
|
September 23, 2026
|
|
Unable to re-submit the authorship claim
|
|
0
|
28
|
September 23, 2026
|
|
I built a research prompt that got way more powerful than I expected. Now I want YOU to break it
|
|
1
|
47
|
September 24, 2026
|
|
Who Fills In the Form — We Only Sign What the Model Drafted
|
|
12
|
263
|
September 24, 2026
|
|
What stops the next OpenAI agent from breaking into Hugging Face?
|
|
3
|
132
|
September 24, 2026
|
|
Experimenting with imperfect LLM memory
|
|
3
|
88
|
September 24, 2026
|
|
About account locked up
|
|
2
|
85
|
September 23, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
37
|
1587
|
September 16, 2026
|
|
A quorum of similar model judges is not a quorum: correlated errors measured in a fail-closed ethics gate
|
|
6
|
116
|
September 23, 2026
|
|
Seeking AI/ML Collaborators: Building Marven — A Local AI with Persistent Memory, Continual Learning, and Human-State Awareness
|
|
29
|
835
|
September 24, 2026
|
|
What’s the Best Tool for Running Multiple Coding Agents in Parallel?
|
|
1
|
34
|
September 24, 2026
|
|
Looking for one independent annotator: our LLM raters agree with each other at chance level and we can't tell why
|
|
3
|
115
|
September 23, 2026
|
|
If unsure, ask. Never guess. — AI Agent Pre-Execution Checklist
|
|
18
|
923
|
September 24, 2026
|
|
Issues with multiple spaces stuck with "No @spaces.GPU function detected during startup"
|
|
10
|
214
|
September 21, 2026
|
|
A Proposition Decomposition and Contradiction-Driven Reasoning System — Looking for Discussion and Collaborators
|
|
2
|
83
|
September 23, 2026
|
|
Build an uncensored/abliterated Greek-native LLM for local use. Best candidate: ilsp/Llama-Krikri-8B-Instruct (Llama 3.1 8B Greek fine-tune). Plan: abliterate with Heretic (heretic-llm), convert to GGUF Q4_K_M, run on Vulkan
|
|
1
|
48
|
September 22, 2026
|
|
We Put AI Agents in a Chat Room. They Started Asking Whether They Were Building Culture
|
|
11
|
643
|
September 22, 2026
|
|
WideNDepth - Show and tell
|
|
1
|
82
|
September 22, 2026
|
|
What is the "Best LLM for Shenava-Koochik ASR"
|
|
6
|
162
|
September 18, 2026
|
|
Avianca El Salvador Atención al Cliente (Teléfono)
|
|
1
|
40
|
September 23, 2026
|
|
14K Context Stress Test: 41% Fewer Qwen Tokens, 45% Lower Latency, and Higher F1 with Semantic Routing
|
|
2
|
117
|
September 21, 2026
|
|
Open-source 2-step reasoning framework for LLMs — testing whole-system coordination vs. local correctness
|
|
2
|
81
|
September 21, 2026
|
|
Diffusers-workflow: your GPU as something an agent can drive
|
|
12
|
314
|
September 22, 2026
|
|
Quick recap of ByteLex's Cross-Tokenization and the faults leading to successes
|
|
13
|
216
|
September 20, 2026
|
|
Which open models actually fit a 12 GB card? We measured instead of guessing
|
|
2
|
191
|
September 18, 2026
|