|
Request to update paper title: arXiv 2610.02205
|
|
0
|
25
|
October 12, 2026
|
|
Useful parameter for Model/Dataset/Space search
|
|
3
|
121
|
October 10, 2026
|
|
Coordinated spam wave flooding the "New" topics feed
|
|
2
|
120
|
October 12, 2026
|
|
Do you Think Removing the $0.10 Monthly Free Inference Credits Is the Right Decision?
|
|
2
|
140
|
October 9, 2026
|
|
Janas-LLM 37 tok/s vs llama.cpp 2.8 tok/s on Qwen3-Next-80B, on an Intel Core Ultra 9 185H with 32 GB RAM
|
|
0
|
51
|
October 11, 2026
|
|
Shoe string ablation or pruning
|
|
7
|
147
|
October 12, 2026
|
|
How Do You Choose the Right AI Model for a Real Workflow?
|
|
0
|
32
|
October 12, 2026
|
|
Sanity check on my hybrid RAG settings
|
|
1
|
30
|
October 12, 2026
|
|
What does a AI judge score of 0.8 actually mean? Introducing Typed Evals
|
|
0
|
63
|
October 10, 2026
|
|
How to improve my tokens per second?
|
|
1
|
90
|
October 10, 2026
|
|
Did HuggingFace remove the credits given to Free Users?
|
|
5
|
277
|
October 10, 2026
|
|
What do you think about AI?
|
|
21
|
953
|
October 9, 2026
|
|
The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They're Wrong
|
|
9
|
221
|
October 10, 2026
|
|
Open Source Engineering Challenge - HELP!
|
|
0
|
46
|
October 11, 2026
|
|
We gave AI a trust we never gave people - The third axis, after capability and permission
|
|
10
|
437
|
October 8, 2026
|
|
Keeping the Attention Sink Exact in Activation-Whitened SVD Compression
|
|
2
|
87
|
October 11, 2026
|
|
Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute
|
|
0
|
58
|
October 10, 2026
|
|
Find Your Planet
|
|
0
|
36
|
October 11, 2026
|
|
Scaling Beatrix V3: a 376M byte-level model and the training
|
|
9
|
167
|
October 11, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
37
|
1823
|
September 16, 2026
|
|
An open research lab for measuring — not prompting — music production in a DAW
|
|
14
|
385
|
October 10, 2026
|
|
AI, Mathematics, and the Possibility of an “Information Field”
|
|
2
|
103
|
October 9, 2026
|
|
Full-Stack 20B 1.58-bit LLM Codebase: Run Private, High-Throughput AI Completely Offline on Consumer Hardware
|
|
2
|
70
|
October 11, 2026
|
|
Misalignment is not required for an agent to act without authorization
|
|
28
|
703
|
October 10, 2026
|
|
Is 3B Always Better Than 1.5B? Why Qwen2.5-1.5B Beat 3B in Our Long-Context Benchmark
|
|
2
|
84
|
October 10, 2026
|
|
Could RAG retrieve LLM-native latent memory instead of text?
|
|
3
|
93
|
October 12, 2026
|
|
Ways to improve my tokens / second
|
|
2
|
76
|
October 10, 2026
|
|
The text we compare with the first message changed the cluster match from 21% to 92%. How do we find which change mattered?
|
|
2
|
81
|
October 9, 2026
|
|
Please provide a way to block undesirable people
|
|
2
|
164
|
October 11, 2026
|
|
Consciousness as a puzzle, the observer as a mirror, and AI's place in this circle
|
|
60
|
1190
|
October 12, 2026
|