AI
57 bites tagged AI — interview questions with model answers, and 60-second explainers.
LLMs Get 'Lost in the Middle' of Long Contexts
LLMs struggle to find information buried in the middle of long prompts. Performance is highest when key facts are at the beginning or end of the context. This impacts multi-document QA and RAG.
Tree of Thoughts: LLM Reasoning Beyond a Single Path
Tree of Thoughts (ToT) lets an LLM explore multiple reasoning paths at once, like a human brainstorming. It generates several 'thoughts' and pursues the most promising ones. This is crucial for planning tasks where one wrong turn fails.
Least-to-Most Prompting: Solving Hard Problems Incrementally
Least-to-most prompting guides an LLM by breaking a hard problem into a sequence of simpler steps. It excels at complex math or logic where chain-of-thought fails, solving each subproblem using the answer to the previous one.
Chain-of-Thought Prompting: Making LLMs 'Show Their Work'
Chain-of-Thought (CoT) prompting gets better answers from LLMs by asking them to 'show their work.' It's best for complex reasoning like math problems or logic puzzles where breaking the problem down helps.
Prompt Engineering: Guiding LLMs to Better Answers
Prompt engineering is like being a director for an LLM actor: you provide context and constraints to get the desired performance. It's used to build reliable AI features and test model limits.
What is a Large Language Model (LLM)?
An LLM is a neural network trained on vast text data to process and generate human-like language. It's the core technology behind chatbots, enabling them to generate, summarize, and translate text. Its reliability depends entirely on its training data.
Activation Functions: Making Neural Networks Nonlinear
An activation function acts as a gatekeeper for a neuron, deciding what signal to pass on. It introduces non-linearity, allowing networks to learn complex patterns. A network with only linear activations collapses into a simple, less powerful model.
Semantic Search: Finding Meaning, Not Just Keywords
Semantic search finds meaning, not just keywords. It's like asking a librarian for 'books about space travel' and getting results for 'astronaut biographies,' not just titles with the exact words. It's used in search engines to find conceptually related items.
Vector Databases: Searching by Meaning, Not Keywords
A vector database finds "what's most like this?" instead of "find me exactly this." It organizes data by semantic meaning, not just exact values, making it ideal for recommendation engines, semantic search, or finding similar images.
AI Safety: Preventing Unintended Consequences
AI Safety is the engineering discipline for preventing intelligent systems from causing harm, by accident or misuse. It's crucial for autonomous systems like self-driving cars or large models that can amplify bias.
AI Transparency: Explaining the Black Box's 'Why'
AI transparency means seeing the 'why' behind an algorithm's decision, not just its code. It's vital for high-stakes systems like credit scoring or news feeds. The footgun is thinking open-sourcing the model is enough; true transparency explains the logic.
Algorithmic Bias: When Code Creates Unfair Outcomes
Algorithmic bias is a mirror reflecting flawed human data, leading to systematically unfair outcomes. It appears in hiring tools favoring one gender or loan systems denying certain groups. The footgun is assuming tech is neutral; the bias is in the data.
Q-Learning: Teaching an Agent by Trial and Error
Q-Learning teaches an agent the 'quality' of an action in a given state through trial and error, like training a pet with treats. It's used in robotics for navigation or in games where an AI learns optimal moves.
Artificial Neural Networks: Learning from Examples
Think of an ANN as a digital brain that learns from examples, not explicit code. It's a network of simple nodes that adjust their connections to spot patterns. They power image recognition and language translation, but are only as good as their training data.
Semantic Scene Classification: Understanding Context, Not Just Objects
Scene classification tells you the context of an image ("this is a forest"), not just the objects in it ("there's a tree"). It's used by self-driving cars to identify a highway vs. a residential street and by apps to organize photos.
Edge AI Accelerators: Inference Without the Cloud
An Edge AI accelerator is a specialized, low-power chip that runs AI models directly on a device, skipping the cloud. It's used for real-time tasks like object detection where latency and privacy are critical.
Image Captioning: Teaching Machines to Describe What They See
Image captioning teaches a computer to generate a human-readable sentence describing an image, translating pixels into words. This powers accessibility features and better image search.
CLIP: Teaching AI to See with Words
CLIP creates a shared map for images and text, letting you classify images with natural language prompts. It's used for zero-shot classification and semantic search, bypassing the need for task-specific labeled data.
Action Recognition: Teaching Machines to Understand 'Doing'
Action recognition teaches computers to understand *what* is happening in a video by analyzing motion over time. It's used for fall detection in healthcare, sports analysis, and security. The footgun is confusing it with single-frame object detection.
Explainable AI (XAI): Why Did the Model Do That?
Explainable AI (XAI) translates a model's 'black box' decision into a human-readable reason. Use it to debug predictions, build user trust, or meet regulatory needs. The footgun: explanations are approximations of the model's logic, not absolute truth.
Cloud Computer Vision: Renting an AI's Eyes via API
Think of it as an API that lets your app 'see.' You send an image and get back structured data like object labels or text. It's used for content moderation, digitizing documents, or making photo libraries searchable.
Pre-trained AI Services: Renting Expertise, Not Building It
Pre-trained AI services are like renting an expert's brain via an API. Instead of training your own model, you call a service for tasks like speech-to-text or image analysis. The footgun is assuming a general model will master your specific industry jargon.
Extrinsic vs. In-Context: Two Types of LLM Hallucination
LLM hallucinations split into two types: in-context, where output contradicts provided sources, and extrinsic, where it conflicts with world knowledge. This distinction is critical for engineers debugging AI systems, as RAG pipelines fight in-context errors while open-ended generation faces extrinsic ones. Mitigating extrinsic hallucinations requires models to not only be factual but also to admit when they don't know an answer, a major challenge given the impracticality of verifying against tra
OpenAI's GPT-5.2 Derives New Physics
OpenAI's GPT-5.2 derived a new theoretical physics result for 'single-minus gluon tree amplitudes,' a finding previously thought impossible. This demonstrates a shift from LLMs regurgitating training data to performing novel scientific reasoning. Physicist Alex Lupsasca found that while GPT-5's general skills seemed stagnant, its frontier capabilities exploded, reproducing a complex paper in 11 minutes. This suggests expert 'priming' can unlock high-level reasoning in foundation models for compl
Get AI bites daily.
Five a day, five minutes, offline. With quizzes so it sticks.
Open testing — you’ll join as an early tester.