|
Phys-ai-dataprofiler — know whether a dataset is good enough before you download 500 GB
|
|
1
|
16
|
November 15, 2026
|
|
Best AI WebUi to interact with local LLM AI
|
|
0
|
32
|
November 14, 2026
|
|
Benchmarking System One small LLM decision APIs vs. in-process tree ensembles and exact TreeSHAP on 64-feature tabular payloads
|
|
2
|
27
|
November 15, 2026
|
|
Peanut v2 - A more stable Adam variant, tested on CPU only. Try it on your dataset?
|
|
4
|
56
|
November 14, 2026
|
|
How do you decide which model to start with for a first project?
|
|
1
|
19
|
November 14, 2026
|
|
Talking Heads: chess where the pieces have opinions—and the players can answer
|
|
2
|
52
|
November 14, 2026
|
|
We gave AI a trust we never gave people - The third axis, after capability and permission
|
|
37
|
1041
|
November 14, 2026
|
|
The AI safety question may be backwards
|
|
7
|
142
|
November 14, 2026
|
|
Training a Tiny Language Model to Follow Prompts Across 6 Low Resource Lanuages
|
|
1
|
40
|
November 14, 2026
|
|
Member needs help with account
|
|
2
|
36
|
November 13, 2026
|
|
Agentmetry: an open-source record of what your coding agent did on your machine Category: Show and Tell
|
|
5
|
80
|
November 14, 2026
|
|
Freedream-1B-Instruct V1.1 from scratch published!
|
|
1
|
80
|
November 14, 2026
|
|
Questions about GGUF
|
|
3
|
128
|
November 13, 2026
|
|
HF Jobs: Can I delete cron job history?
|
|
1
|
52
|
November 12, 2026
|
|
Open-Source LLM Evaluation and Annotation QA Benchmark
|
|
4
|
82
|
November 14, 2026
|
|
Multi-Agent Orchestration in Practice: 44 Autonomous Agents in a Desktop Workstation (KIRA Company Director)
|
|
1
|
34
|
November 14, 2026
|
|
Alfós' Four Laws of Agentics: rethinking Asimov's laws for AI agents after the Hugging Face incident
|
|
1
|
30
|
November 14, 2026
|
|
How much of AI spending is paying a model to reread its job description?
|
|
4
|
77
|
November 14, 2026
|
|
GhostMind: An Experimental Self-Improving Intelligence Engine — Real-World Blind Discovery Results
|
|
2
|
65
|
November 13, 2026
|
|
Luthn: self-hosted shared memory for Codex and Claude Code
|
|
3
|
81
|
November 13, 2026
|
|
My AI agent kept saying “done” when nothing happened, so I built Deed. Would love feedback
|
|
4
|
85
|
November 13, 2026
|
|
Linear Regression performs well overall but significantly underestimates long delivery durations. How should I investigate this?
|
|
2
|
39
|
November 14, 2026
|
|
What are the current trends in robot imitation learning and VLA, and what are the main challenges of existing policy architectures?
|
|
1
|
56
|
November 15, 2026
|
|
Feedback wanted: scenario-based ethical evaluation tool for models and agents
|
|
3
|
76
|
November 11, 2026
|
|
Coding or Cheating? An Investigation of Frontier Coding LLMs
|
|
1
|
59
|
November 12, 2026
|
|
Making a GUI-only GPU poker solver scriptable — and what solver-priced regret reveals about heuristic bots
|
|
4
|
104
|
November 14, 2026
|
|
Ru-Jev v1.3: label augmentation helps with unfamiliar words, not abbreviations or codes (10 vocabularies, 2 candidate-set sizes, per-row files included)
|
|
6
|
89
|
November 10, 2026
|
|
Experimenting with Human + AI Filmmaking
|
|
1
|
43
|
November 12, 2026
|
|
343 calibration matches did not establish semantic conformance
|
|
2
|
66
|
November 11, 2026
|
|
EpiGauge: A benchmark for T-cell immunogenicity prediction from Norvara Therapeutics
|
|
2
|
45
|
November 14, 2026
|