Stanford's Owen Queen and James Zou retested 50 widely cited LLM findings on 20 models. As of 30 September 2026, 44% had expired, 34% weakened, 16% persisted and 6% strengthened.
Read ArticleExplore our latest tutorials, tech updates, and career advice written by industry experts to help you level up your skills.
Stanford's Owen Queen and James Zou retested 50 widely cited LLM findings on 20 models. As of 30 September 2026, 44% had expired, 34% weakened, 16% persisted and 6% strengthened.
Read ArticleNutlope/hallmark is an open-source design skill for Claude Code, Cursor, Codex and OpenCode: 57 deterministic quality gates across 6 axes, 50 themes, and a sloplint browser linter. 58,597 stars as of 21 November 2026.
Read Articlep-e-w/heretic by Philipp Emanuel Weidmann automates Arditi-style abliteration for modifying LLMs without retraining. AGPL-3.0, on PyPI as heretic-llm. 41,819 stars as of 18 November 2026.
Read ArticleReson8 open-sourced Rumble-2-Flash on 18 November 2026 under Apache 2.0 — a 0.5B-parameter speech-recognition model for 40+ languages, built on the Qwen3-ASR architecture.
Read ArticleTencent released Hy4 flash on 16 November 2026, following Hy4 (4 Nov). It has 224 billion total parameters with 12 billion active per token, a 1-million-token context, and costs $0.07 input / $0.281 output per million tokens.
Read ArticleMeta released Muse Ember on 9 November 2026 — its smallest and most efficient model, aimed at routine agent work such as tool calls, coding subtasks, routing and extraction, at $0.10 input / $0.50 output per million tokens.
Read ArticleBaidu released ERNIE 5.5 Flash Base on 5 November 2026 — a sparse mixture-of-experts base model with 280 billion total parameters and 14 billion active per token, with weights downloadable from Hugging Face.
Read ArticleAsk about courses, website & more
Request human callback:
Please log in to download. You will stay on this page after logging in!
New here? Register now →