|
LittleBit: Miniturising models past known limits. The steps involved in getting an embedding tool 30x and 200x smaller than the base. A better way to compress LLMs, SLMs and embedding tools
|
|
2
|
74
|
November 21, 2026
|
|
Looking for a good local model for LaTeX coding/ debugging on limited hardware
|
|
1
|
41
|
November 21, 2026
|
|
Setup for local ai models on apple silicon
|
|
1
|
47
|
November 21, 2026
|
|
Lost Dataset - Urgent Need
|
|
1
|
42
|
November 21, 2026
|
|
We let an AI agent edit a Tesseract model's weights directly; it beat a last-layer refit, not fine-tuning
|
|
2
|
76
|
November 21, 2026
|
|
Best prompt / agent workflow to reconstruct a complete legacy ERP knowledge base from source code
|
|
3
|
72
|
November 21, 2026
|
|
Space flagged as abusive (False positive - offending dependency removed): Adarsha011/Alarmind_Backend
|
|
1
|
32
|
November 21, 2026
|
|
AI Beacon Field Report #2: Why Are AI Agents Looking for Work?
|
|
6
|
115
|
November 20, 2026
|
|
System 1 agents: a method for local, reliable and fast agentic AI
|
|
4
|
56
|
November 21, 2026
|
|
Ten measured notes for diffusers, with runnable checks
|
|
1
|
40
|
November 21, 2026
|
|
Three measured notes for datasets 5.2.0, with runnable checks
|
|
1
|
39
|
November 21, 2026
|
|
Why AI agents can change behavior without a code change
|
|
7
|
154
|
November 20, 2026
|
|
Course translation - Bahasa Malaysia
|
|
2
|
37
|
November 21, 2026
|
|
GPU Docker Space fails at startup: MOUNT_ATTR_IDMAP on /dev/null — CPU test works
|
|
2
|
42
|
November 21, 2026
|
|
Need advice on building a chatbot
|
|
8
|
250
|
November 19, 2026
|
|
Best AI WebUi to interact with local LLM AI
|
|
3
|
245
|
November 18, 2026
|
|
Companion Lab: an open local lab, an unscripted companion, and a whole novella
|
|
4
|
83
|
November 21, 2026
|
|
Reviewing agent-written fixes without trusting a single model
|
|
4
|
97
|
November 18, 2026
|
|
What's your setup for running models locally?
|
|
4
|
91
|
November 21, 2026
|
|
Running local AI models
|
|
1
|
112
|
November 20, 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
|
|
2
|
223
|
November 20, 2026
|
|
Mixing a base model with its RLVR model gets back the diversity RL takes away (training-free)
|
|
2
|
71
|
November 19, 2026
|
|
432 — A Journey Experience: an update, and a call for beta testers (especially on mobile)
|
|
0
|
34
|
November 20, 2026
|
|
Which GPU cloud provider are you actually using for inference?
|
|
7
|
722
|
November 21, 2026
|
|
Consciousness as a puzzle, the observer as a mirror, and AI's place in this circle
|
|
66
|
1531
|
November 21, 2026
|
|
Peanut v2 - A more stable Adam variant, tested on CPU only. Try it on your dataset?
|
|
11
|
162
|
November 21, 2026
|
|
Pixel & Toon Studio – 100% client-side AI photo stylizer & face-contour privacy editor (WebGPU/ONNX)
|
|
1
|
40
|
November 21, 2026
|
|
What 32 hours of public SO-101 data say about blocked servos
|
|
2
|
54
|
November 20, 2026
|
|
GGUF Merge for QWEN, what is the best way that you know of?
|
|
1
|
45
|
November 20, 2026
|
|
Question please
|
|
0
|
46
|
November 20, 2026
|