|
About the Show and Tell category
|
|
0
|
1010
|
January 26, 2023
|
|
I built a deterministic execution-governance layer for AI agents. Where does it break?
|
|
7
|
152
|
September 10, 2026
|
|
My new app Medicine Study AI
|
|
1
|
46
|
September 9, 2026
|
|
Reproducing a LeRobot regression with TraceML
|
|
3
|
104
|
September 9, 2026
|
|
Introducing Calibra: Robot Dataset Observability for LeRobot (Space + Benchmark)
|
|
3
|
130
|
September 9, 2026
|
|
At some point, “memory + persona” stops being an adequate description
|
|
11
|
296
|
September 9, 2026
|
|
AlphaAvatar v0.6.6: event-driven multimodal memory, unified runtimes, and cleaner agent contracts
|
|
3
|
93
|
September 8, 2026
|
|
PRAMA-Dynamagh: Evidence-Bound Autonomous Execution on Telegraph Protocol
|
|
0
|
25
|
September 8, 2026
|
|
Importing Spaces into a public agent run-record — and the attestation gap we hit
|
|
1
|
29
|
September 7, 2026
|
|
Project Shadow: A CAPA Can Close Without Fixing Anything (A System for AI and Civic QA)
|
|
2
|
107
|
September 7, 2026
|
|
A Practical AI Workflow for Automating Business Lead Qualification
|
|
0
|
20
|
September 7, 2026
|
|
Niodoo interpretability and the cybernetics loop
|
|
1
|
70
|
September 7, 2026
|
|
AI Model Radar – measured hardware fit for open models (real GGUF sizes + per-architecture KV cache), with a JSON API and MCP server
|
|
0
|
18
|
September 6, 2026
|
|
Mlx-smolvla: SmolVLA checkpoint execution and validation on Apple Silicon
|
|
2
|
97
|
September 6, 2026
|
|
You fine-tune on customer data with SFTTrainer. Can you prove it didn’t memorize? memaudit runs that audit inside your training job
|
|
0
|
13
|
September 6, 2026
|
|
You fine-tune on customer data with SFTTrainer. Can you prove it didn't memorize? memaudit runs that audit inside your training job
|
|
0
|
14
|
September 6, 2026
|
|
Vyact: a local AI workspace connecting GGUF and MLX models with document search
|
|
0
|
10
|
September 5, 2026
|
|
Does the Rust ML community need a pure Rust alternative to Gradio? (Seeking feedback on grio)
|
|
0
|
15
|
September 4, 2026
|
|
HF Agent OS — a multi-agent system for managing the full Hugging Face project lifecycle (built with smolagents)
|
|
2
|
111
|
September 3, 2026
|
|
DFlash Console: Windows control panel for llama-server and DFlash 1/2 speculative decoding
|
|
0
|
19
|
September 3, 2026
|
|
Deterministic LoRA training directly through quantized GGUF serving weights
|
|
11
|
322
|
September 3, 2026
|
|
I made the PathMap.org software, and today I open sourced it!
|
|
0
|
9
|
September 2, 2026
|
|
MemEval & PropMem: Standardizing Agent Memory Benchmarks
|
|
1
|
318
|
September 2, 2026
|
|
Model X-Ray — layer-by-layer scans of open checkpoints (free open beta)
|
|
0
|
10
|
September 1, 2026
|
|
SKYNET800 (alfa) Killing AI hallucinations with resonance
|
|
14
|
267
|
September 1, 2026
|
|
Tutorial: Build and Train a Byte-Level BPE Tokenizer From Scratch
|
|
2
|
108
|
September 1, 2026
|
|
Show and Tell: A stdio MCP server for sending email from AI agents
|
|
0
|
6
|
September 1, 2026
|
|
Beta‑testing API Gateway for Chinese‑origin LLMs — Free Test Quota for Feedback
|
|
2
|
91
|
August 31, 2026
|
|
ConceptNet — 4-layer enterprise voice intent classifier, 98.6% accuracy, 9 languages, token-free, open source
|
|
5
|
140
|
August 30, 2026
|
|
Open-source memorization/privacy auditor for Trainer/TRL fine-tunes — canary MIA + regurgitation testing (with a real case study)
|
|
3
|
134
|
August 30, 2026
|