AI/TLDR — New AI Releases Daily: Models, Tools, Repos & PapersA high-volume feed of new AI releases — models, open-source repos, developer tools, papers, datasets, and benchmarks — refreshed every 2 hours. Each release is explained in plain English so you actually understand what shipped.This site uses JavaScript to render the interactive feed. Enable JavaScript, or visit the source repo for the raw JSON.

AI/TLDR

SYSTEM 13/14 · THE FIELD GUIDE

Evaluation & Safety

Measuring whether models are good — and keeping them from being bad.

5 TRACKS63 ARTICLESbeginner → advanced

Evaluation Basics

Because "it looks good to me" is not a test suite.

LLM EvalsBEGINNER Building an Eval SuiteINTERMEDIATE Golden DatasetsBEGINNER Your First EvalBEGINNER Code vs Model vs Human GradingINTERMEDIATE Eval MetricsINTERMEDIATE Regression Testing PromptsINTERMEDIATE Eval in CI/CDINTERMEDIATE Offline vs Online EvalsINTERMEDIATE Eval Sample SizeINTERMEDIATE Ragas LibraryINTERMEDIATE DeepEvalINTERMEDIATE PromptfooINTERMEDIATE lm-evaluation-harnessINTERMEDIATE Inspect (AISI)INTERMEDIATE OpenAI EvalsINTERMEDIATE

LLM-as-a-Judge

Using models to grade models — and when to distrust the grader.

Using Models to Grade ModelsBEGINNER Common PitfallsINTERMEDIATE Judge BiasesINTERMEDIATE Pairwise vs Rubric ScoringINTERMEDIATE Calibrating a JudgeINTERMEDIATE Reference-Free vs Reference-BasedINTERMEDIATE Chain-of-Thought JudgingINTERMEDIATE Judge vs Human AgreementADVANCED AI Grading AIINTERMEDIATE G-EvalINTERMEDIATE

Benchmarks & Leaderboards

MMLU to SWE-bench to LMArena — what the scores mean and when they lie.

LLM BenchmarksBEGINNER Chatbot Arena (LMSYS)BEGINNER Coding BenchmarksBEGINNER LMArena & Elo RatingsBEGINNER Agent BenchmarksINTERMEDIATE Benchmark ContaminationINTERMEDIATE Benchmark OverfittingINTERMEDIATE Public vs Private BenchmarksBEGINNER Reading a Benchmark ScoreBEGINNER MMLUINTERMEDIATE GPQAINTERMEDIATE SWE-benchINTERMEDIATE ARC-AGIINTERMEDIATE Artificial AnalysisINTERMEDIATE Stanford HELMINTERMEDIATE

Red Teaming & Jailbreaks

Attack your own AI before someone else does.

AI Red TeamingBEGINNER LLM JailbreaksBEGINNER Common Attack FamiliesINTERMEDIATE Automated vs Manual Red TeamingINTERMEDIATE Adversarial PromptsBEGINNER GarakINTERMEDIATE Microsoft PyRITINTERMEDIATE

Alignment & Safety Basics

Why models refuse, how they're steered, and the bigger risk map.

AI AlignmentBEGINNER Mechanistic InterpretabilityADVANCED SycophancyBEGINNER Refusals & Over-RefusalsBEGINNER Safety vs SecurityINTERMEDIATE Constitutional AIINTERMEDIATE Measuring BiasINTERMEDIATE Reward HackingINTERMEDIATE Specification GamingINTERMEDIATE RLHF vs RLAIFINTERMEDIATE Llama GuardINTERMEDIATE Guardrails AIINTERMEDIATE NeMo GuardrailsINTERMEDIATE Microsoft PresidioINTERMEDIATE LLM GuardINTERMEDIATE