|
Inference, semantics, questioning
|
|
2
|
37
|
September 27, 2026
|
|
What if a small LLM didn't have to make every decision?
|
|
10
|
256
|
September 26, 2026
|
|
Cad/sldw mcp tool using
|
|
2
|
44
|
September 27, 2026
|
|
Misalignment is not required for an agent to act without authorization
|
|
21
|
378
|
September 28, 2026
|
|
What do you think about AI?
|
|
17
|
565
|
September 26, 2026
|
|
All paid GPU pools fail to start: MOUNT_ATTR_IDMAP error at container init (Exit code 128)
|
|
3
|
95
|
September 25, 2026
|
|
Free cpu-basic quota is 0 on new account
|
|
1
|
28
|
September 27, 2026
|
|
Is provider KV caching sufficient for agent swarms and long run agents?
|
|
1
|
46
|
September 27, 2026
|
|
Modifying a Qwen 2.5 Omni 3B model architecture to stop visual interference when slide context is given along with audio
|
|
3
|
51
|
September 28, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
37
|
1616
|
September 16, 2026
|
|
What do you think about Jev?
|
|
3
|
66
|
September 28, 2026
|
|
Should we arrest Altman and Amodei?
|
|
1
|
48
|
September 27, 2026
|
|
Nvidia RTX 5060
|
|
1
|
61
|
September 27, 2026
|
|
Exit code: 128. Reason: failed to create containerd task:
|
|
1
|
48
|
September 27, 2026
|
|
Seeking arXiv cs.CV endorsement: a silent failure mode in overfitted neural image codecs (code + data public)
|
|
2
|
44
|
September 28, 2026
|
|
What extra to add in gradient descent optimization algorithm? [SUGGESTION]
|
|
2
|
49
|
September 27, 2026
|
|
Meta-Llama-3-8B-Instruct access request pending for several weeks with no response from Meta
|
|
1
|
33
|
September 27, 2026
|
|
What has your experience with knowledge distillation been like?
|
|
1
|
30
|
September 27, 2026
|
|
A quorum of similar model judges is not a quorum: correlated errors measured in a fail-closed ethics gate
|
|
7
|
153
|
September 26, 2026
|
|
Call for testers: Janas, a CPU-only engine that runs MoE models larger than RAM — one command to test your machine
|
|
1
|
40
|
September 27, 2026
|
|
What stops the next OpenAI agent from breaking into Hugging Face?
|
|
14
|
280
|
September 28, 2026
|
|
VeriLoop E2 Release: 27B Post-Trained Model and Full GGUF Precision Ladder from BF16 to IQ1_M
|
|
2
|
1044
|
September 27, 2026
|
|
Is Machine Translation Solved?
|
|
5
|
103
|
September 27, 2026
|
|
Biological JEPA: Modeling Disease Progression with Biological Constraints
|
|
1
|
33
|
September 27, 2026
|
|
SplitMOE- similar to deepseek-MOE `same same but different`
|
|
2
|
118
|
September 23, 2026
|
|
Experimenting with imperfect LLM memory
|
|
7
|
158
|
September 24, 2026
|
|
How much VRAM do you realistically need to fine-tune small models on a laptop?
|
|
2
|
113
|
September 24, 2026
|
|
The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They're Wrong
|
|
4
|
93
|
September 27, 2026
|
|
Learning about recursive self-improvement — looking for feedback on my experimental framework
|
|
3
|
103
|
September 23, 2026
|
|
Making local LLM + TTS work for a Persian voice assistant on a GTX 1650 Ti (4GB VRAM) — looking for advice
|
|
7
|
186
|
September 21, 2026
|