Context Rot: How Increasing Input Tokens Impacts LLM Performance
Chroma. Kelly Hong walking through Chroma's research on 18 models — why needle-in-haystack scores are misleading, how performance degrades with ambiguity and distractors, why even simple string-repetition tasks degrade past 500 tokens. Short, evidence-based, and exactly the case the article needs you to take seriously before getting to the engineering moves.
AI Expert note
Model names, pricing and capabilities change quickly. Use this for the decision pattern, then verify current model behavior before adopting it.
What you should get from this
Understand how long context can fail under ambiguity and distractors, then design tests around that risk.
Watch next
Continue through the same learning path with the next curated companion videos.
44 minutesBuilding Brain-Like Memory for AI | LLM Agent Memory Systems
A longer implementation pass through the cognitive-science-inspired categories — episodic, semantic, working, procedural — wired into an agent in code.
Watch next
5 minutesClaude has taken control of my computer...
Understand why screenshot-based computer use is powerful, slow, expensive and brittle compared with API-native automation.
Watch next
17 minutesDefending LLM - Prompt Injection
Review prompt-injection defenses such as taint analysis, output-shape restrictions, user isolation, deterministic settings and redundant checks for critical paths.
Watch nextRelated videos
Take it further
Hand-picked external courses that go deeper on this topic.
DeepLearning.AIChatGPT Prompt Engineering for Developers
Ninety minutes to a year's worth of intuition. If you've started writing code that calls an LLM — or you're about to — this is the most efficient course online for closing the gap between "playing with ChatGPT" and "shipping a feature that calls an LLM."
Coursera · Vanderbilt UniversityPrompt Engineering for ChatGPT
The academic complement to DeepLearning.AI's short course — same discipline, longer arc, written for people who don't code. Dr. White teaches prompting as a set of reusable patterns (Ask for Input, Outline Expansion, Fact Check List, Menu Actions) rather than tricks. After this you'll prompt LLMs like a designer, not a guesser.