📚 All Articles

115 guide(s) — regularly updated

All levels 🟢 Beginner 🟡 Intermediate 🔴 Advanced
LLM & Modèles 🟢 Débutant 14 min

Gated DeltaNet-2 : the Yejin Choi paper that solves the oldest problem of linear attention

Discover Gated DeltaNet-2, Yejin Choi's paper that finally solves the oldest problem of linear attention in AI models.

2026-05-23 17:03
LLM & Modèles 🟢 Débutant 12 min

Cursor Composer 2.5: The coding model that rivals Opus 4.7 at a tenth of the price

Discover Cursor Composer 2.5, a coding model rivaling Claude Opus 4.7 at a tenth of the price. AI price war analysis.

2026-05-22 16:04
LLM & Modèles 🟢 Débutant 15 min

DeepWeb-Bench: The new benchmark that exposes the weaknesses of AI search agents

Discover DeepWeb-Bench, the new benchmark proving AI search agent scores are inflated and exposing their true weaknesses.

2026-05-21 18:01
LLM & Modèles 🟢 Débutant 11 min

Gemini 3.5 Flash : the fast model that beats Opus 4.7 and GPT-5.5 on agent benchmarks — 289 tokens/second

Discover Gemini 3.5 Flash: the ultra-fast model at 289 tokens/sec beating Claude Opus 4.7 and GPT-5.5 on agent benchmarks.

2026-05-20 14:09
LLM & Modèles 🟢 Débutant 14 min

General Preference RL: this paper unifies reinforcement learning and preference optimization for LLMs

Discover the General Preference RL paper unifying reinforcement learning and preference optimization to solve LLM post-training.

2026-05-19 18:01
LLM & Modèles 🟢 Débutant 12 min

OpenAI Parameter Golf: The challenge that proves small models are the future of AI

Discover the OpenAI Parameter Golf challenge: why compressing an LLM into 16 MB proves small models are the future of AI.

2026-05-18 17:02
LLM & Modèles 🟢 Débutant 15 min

Meta Muse Spark: why Meta betrayed open-source — the first closed model from the Superintelligence Lab

Discover why Meta Muse Spark is a turning point: the first closed model from the Superintelligence Lab that betrays Meta's open-source promise.

2026-05-18 15:04
LLM & Modèles 🟢 Débutant 14 min

MeMo : Memory as a Model — memory as an autonomous model for updating LLMs without retraining

Discover MeMo (Memory as a Model): the innovative solution to update LLMs without retraining and defeat knowledge obsolescence.

2026-05-16 19:01
LLM & Modèles 🟢 Débutant 15 min

SDAR: how to train AI agents with reinforcement learning without breaking them — self-distillation agentic

Discover SDAR (Self-Distillation Agentic Reinforcement): the method to train your AI agents with reinforcement learning without breaking them.

2026-05-16 18:02
LLM & Modèles 🟢 Débutant 13 min

OpenDeepThink : Bradley-Terry comparison-based parallel reasoning changes the game for LLM inference

Discover OpenDeepThink: how Bradley-Terry comparison parallel reasoning revolutionizes LLM inference and outperforms sequential chain-of-thought

2026-05-15 17:05
LLM & Modèles 🟢 Débutant 13 min

Negation Neglect : when fine-tuning makes LLMs blind to the false

Discover the Negation Neglect phenomenon: how fine-tuning LLMs against fake news ends up making them blind to falsehoods.

2026-05-14 19:01
LLM & Modèles 🟢 Débutant 16 min

KV-Fold : The training-free trick that revolutionizes long-context inference in LLMs

Discover KV-Fold, the training-free trick revolutionizing LLM long-context inference and solving the token management nightmare.

2026-05-13 18:06