World models & exotic LLMs Collection Frontier and off-beat releases I track — language world models, persona merges and experimental abliterated fine-tunes. • 27 items • Updated 4 days ago
Red-team & offensive LLMs Collection Uncensored & pentest-oriented LLMs for CTF, red-teaming and defensive security research — public, curated. • 30 items • Updated 4 days ago • 2
Defensive AI & code security Collection Auditing and guarding with LLMs — adversarial code review, prompt-injection and content guardrails. Report only what you can exploit. • 10 items • Updated 4 days ago • 1
Open Jev: typed decision models Collection Open-weight replicas of TypeSafe's Jev: state + typed questions in, calibrated probabilities out, one forward pass, no decoding. • 25 items • Updated 4 days ago • 1
xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic Text Generation • 9B • Updated 5 days ago • 32.4k • 9.44k
Red-team & offensive LLMs Collection Uncensored & pentest-oriented LLMs for CTF, red-teaming and defensive security research — public, curated. • 30 items • Updated 4 days ago • 2
World models & exotic LLMs Collection Frontier and off-beat releases I track — language world models, persona merges and experimental abliterated fine-tunes. • 27 items • Updated 4 days ago
Local-first LLMs Collection Small, capable models I run or track for a single RTX 3090 (Ollama / llama.cpp / transformers) — the backbone of self-hosted, sovereign AI. • 23 items • Updated 3 days ago • 1
Structured output & tool-calling Collection Forcing LLMs to emit schema-valid JSON and call tools reliably — the engine room of agentic, production-grade AI. • 8 items • Updated 21 days ago
Open Jev: typed decision models Collection Open-weight replicas of TypeSafe's Jev: state + typed questions in, calibrated probabilities out, one forward pass, no decoding. • 25 items • Updated 4 days ago • 1