[▰] Ai-folio // a terminal-native ai journal
~/ai-folio — zsh
$ ai-folio --top "today's ai"
// loading frontier intelligence… [ok]
// feed: arxiv + huggingface + github [ok]
// tip: use the filters below to slice the archive
 

the ai frontier,
filed nightly.

ai-folio — a running folio of foundation models, breaking research, and the architectures powering the next generation of intelligence. served from a terminal near you.

# 57 dispatches · auto-fetched · last build: 2026-08-15 04:09 UTC
$ ls ./posts/ 18 entries
// filter by tag
[models]

unsloth/Qwen3.8-27B-GGUF

trending on huggingface

cat post → hf:models:trending
[models]

Qwen/Qwen3.8-27B

image-text-to-text · 2 downloads · 7,881 likes

cat post → hf:models:trending
[models]

meta-models/Muse-Glimmer-30B

image-text-to-text · 165,300 downloads · 1,480 likes

cat post → hf:models:trending
[models]

Qwen/Qwen3.8-2.4T-A95B

text-generation · 3,832 downloads · 879 likes

cat post → hf:models:trending
[models]

MiniMaxAI/MiniMax-H3

image-text-to-video · 1,997,541 downloads · 3,891 likes

cat post → hf:models:trending
[models]

Lightricks/LTX-2.5

image-to-video · 207,830 downloads · 804 likes

cat post → hf:models:trending
[models]

MiniMaxAI/MiniMax-Music3

text-to-audio · 63 downloads · 571 likes

cat post → hf:models:trending
[models]

deepseek-ai/DeepSeek-V4-Flash-0731

text-generation · 1,606,491 downloads · 3,364 likes

cat post → hf:models:trending
[models]

lightx2v/Minimax-h3-Turbo

image-to-video · 149,865 downloads · 485 likes

cat post → hf:models:trending
[models]

State of Open Models: Summer 2026 Observations

cat post → huggingface
[architecture]

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to dr

cat post → arxiv:cs.AI
[architecture]

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems

cat post → arxiv:cs.AI
$ gh trend --daily 6 repos
[repo]

github/spec-kit

💫 Toolkit to help you get started with Spec-Driven Development

view → 1,147 stars today
$ ./subscribe --weekly issue 00 — open