|
About the Show and Tell category
|
|
0
|
919
|
January 26, 2023
|
|
OpOp - The Optimizer Optimizer π§ Because your optimizer is dumb and somebody had to say it
|
|
3
|
12
|
March 1, 2026
|
|
I Built a Persona Library to Assign Expert Roles to Your Prompts
|
|
0
|
19
|
March 1, 2026
|
|
M-Courtyard v0.4.8 β UI/UX Polish Release for macOS AI Training
|
|
0
|
9
|
February 27, 2026
|
|
M-Courtyard - Native Mac app for local fine-tuning (export to LM Studio/Ollama)
|
|
2
|
27
|
February 27, 2026
|
|
Solving agent system prompt drift in long sessions β a 300-token fix
|
|
0
|
9
|
February 26, 2026
|
|
Anubis OSS - Local LLM Benchmarking for Apple Silicon with Real-Time Hardware Telemetry (Looking for Testers + Open Data)
|
|
0
|
23
|
February 25, 2026
|
|
Updated-Grade-School-Math from OpenAI datasets
|
|
1
|
95
|
February 24, 2026
|
|
LitSquare Ink MD β native macOS Markdown editor (token count)
|
|
0
|
9
|
February 23, 2026
|
|
A Harvard PhD 3-day work VS. Openrevise 30 min's work
|
|
2
|
11
|
February 23, 2026
|
|
RomaPy - 180 times faster than python
|
|
2
|
55
|
February 21, 2026
|
|
Let any text speak - with open-source
|
|
2
|
32
|
February 21, 2026
|
|
[Tool] M-Courtyard β GUI for local LLM fine-tuning on Apple Silicon
|
|
0
|
64
|
February 17, 2026
|
|
Entelgia β a dialogue-governed cognitive architecture running fully locally (Ollama)
|
|
1
|
10
|
February 16, 2026
|
|
Why some will have an issue with my work with AI?
|
|
0
|
9
|
February 13, 2026
|
|
RomanAI Performance Milestone: 10.4T Emergent Parameters reached via Qwen2.5:32B
|
|
2
|
11
|
February 12, 2026
|
|
π NanoHammer-1.5B-Instruct:
|
|
0
|
15
|
February 12, 2026
|
|
Trackio + RapidFire AI: Free, Real-Time Experiment Tracking for Parallel Fine-Tuning and RAG Optimization
|
|
2
|
19
|
February 12, 2026
|
|
AI memory problems solved
|
|
8
|
61
|
February 12, 2026
|
|
Restoring a 70B model in ~2 seconds using GPU runtime snapshotting (no warm pools)
|
|
0
|
15
|
February 11, 2026
|
|
Noapi-google-search-mcp - Google Search for local LLMs, no API key
|
|
0
|
67
|
February 11, 2026
|
|
Jailbreak resistance benchmark across 52 recent LLMs (7 levels, redacted outputs)
|
|
1
|
55
|
February 9, 2026
|
|
Hopper β partial orthogonalization changes early reasoning behavior in RL
|
|
1
|
25
|
February 6, 2026
|
|
Force Gemma3:12B to act like a 600B
|
|
2
|
84
|
February 5, 2026
|
|
BarkID: an AI trained on Stanford Dogs
|
|
0
|
20
|
February 4, 2026
|
|
Cohesix 0.4.0-alpha - Open-source MLOps Platform
|
|
0
|
12
|
February 4, 2026
|
|
Update: Making My AI Recruiting Assistant More Deterministic and Auditable
|
|
2
|
38
|
February 3, 2026
|
|
Sharing field notes from a small-scale GRPO + Muon experiment
|
|
2
|
38
|
February 1, 2026
|
|
πΈοΈ WebSense: Web Scraper for Structured Data
|
|
0
|
12
|
January 29, 2026
|
|
Rival - Open-source tool for visually comparing AI model responses
|
|
3
|
366
|
January 28, 2026
|