AI
57 bites tagged AI — interview questions with model answers, and 60-second explainers.
Pre-built AI service vs custom model
Choose a managed service for speed, no ML expertise, and common tasks; build custom for domain-specific needs, control, or cost at scale. buy-versus-build judgment for ML. always building custom when a managed API suffices.
Claude Mythos Cracks Firefox Bugs Fuzzing Missed
Claude Mythos Preview found 20-year-old XSLT and JIT bugs in Firefox that survived years of fuzzing. Mozilla shows AI now catches sandbox escapes and memory corruption. Add LLM security scanning to hardening workflows before attackers adopt them.
AI Use Creates 'Cognitive Debt' in Scrum Teams
Over-relying on AI for sprint planning and backlog refinement creates "Cognitive Debt," eroding a team's problem-solving skills. While AI boosts productivity, it can eliminate the collaborative friction that builds shared understanding and critical reasoning.
AI Turns Specs Into a Programming Language
Spec-Driven Development (SDD) reframes specs as a higher-level programming language for AI agents, not just pre-coding docs. This shifts engineering work from implementation details to defining intent and constraints.
Use AI to Fix Your OKRs, Not Write Them
Use AI to refine your OKRs by creating a custom 'coach' prompt based on expert advice. This avoids leaking company strategy to public LLMs and makes even secure, weaker enterprise models useful for strategic alignment.
Scrum.org's 8-Step Plan for AI-Native Teams
Scrum.org has outlined an 8-step framework to guide teams in becoming 'AI-native.' This structured approach aims to embed AI into all aspects of Scrum, shifting focus from production to evaluation and from 'Definition of Done' to 'Definition of Value'.
DHH Slams 'Luddite' AI Bans in Open Source
Open source projects like Zig and NetBSD are banning AI-assisted code. DHH calls this a 'modern Luddite movement' that betrays the core OSS mission of democratizing software, arguing it's about protecting status, not ensuring quality.
Jira's Rovo AI Aims to Deflect 60% of Tickets
Atlassian's Rovo agents in Jira Service Management aim to deflect up to 60% of repetitive service tickets. The agents intercept requests in Slack or the help portal, providing instant answers from your docs, freeing up support staff for complex engineering…
Study: Disclosing AI use makes you seem 10x lazier
A study of ~1,000 workers found disclosing AI use makes you seem 10x lazier. Even with identical output, peers were 24% less likely to recommend you for key projects. While 94% use AI, the stigma means silence is often the safest career strategy.
Weights & Biases: MLOps for Experiment Tracking & Evaluation
Weights & Biases is a platform for MLOps, providing experiment tracking, evaluation, and observability for AI models. It helps you develop models and ship LLM applications. The main risk it addresses is losing track of which model version used which data.
AI's Dual-Use Problem: Good Tools, Bad Outcomes
AI models built for good can be easily repurposed for harm. A language model that helps with coding can also generate malware. The footgun is assuming good intentions prevent misuse; the risk is in the capability, not the creator's intent.
Model Pruning: Making LLMs Smaller, Not Dumber
Model pruning is surgical weight loss for an LLM, removing neurons or layers to reduce its size. It's used to create smaller, faster versions of models like LLaMA for efficient deployment. The footgun: naive pruning can cripple the model's core capabilities.
World Models: An AI's Internal Simulator for Planning
A world model is an AI's internal simulator, letting it 'dream' about how actions change its environment. This powers robots and autonomous cars, letting them plan complex tasks without real-world trial and error.
AI Auditing: The OWASP LLM Top 10 Checklist
Think of an AI audit like a building inspection for your LLM app, checking for structural weaknesses. It uses frameworks like the OWASP Top 10 to find risks like prompt injection and data leakage.
Bias Mitigation Algorithms: Correcting Unfair AI
Bias mitigation algorithms steer AI toward a defined standard of fairness. They're used in high-stakes systems like hiring or loan approvals to counteract harmful, systemic tendencies learned from biased data.
AI Governance: Rules for Building Intelligent Systems
AI governance creates rules of the road for intelligent systems, ensuring they're safe, fair, and transparent. It applies when governments pass laws or companies form ethics boards. The footgun is treating this as only a legal problem, not a technical one.
ML Interpretability: Cracking Open the Black Box
ML interpretability cracks open the 'black box' to explain *why* a model made a specific decision. It's essential in high-stakes fields like finance or medicine to ensure automated decisions are fair. The footgun is trusting accuracy alone.
The AI Alignment Problem
AI alignment is about making sure an AI pursues our intended goals, not just the literal instructions. It's critical for autonomous systems in medicine or finance. The footgun is assuming a clear objective prevents unintended, harmful outcomes.
HumanEval: Testing if AI-Generated Code Actually Works
HumanEval is a benchmark that tests if an LLM's generated code is functionally correct, not just syntactically valid. It's used to compare models like Codex by having them solve programming puzzles.
Why Elo Ratings for LLMs Can Be Misleading
Elo ranks LLMs like chess players, but models have fixed skills, not dynamic ones. This method powers leaderboards but produces volatile scores, meaning a model's rank can be an unstable estimate of its true, unchanging ability.
HellaSwag: A Benchmark Designed to Fool LLMs
HellaSwag is a commonsense benchmark designed to fool language models. It asks an AI to pick the most logical sentence ending, but the wrong answers are specifically generated to trick machines, not humans. It's used to test for true contextual understanding.
Speech-to-Text (ASR): Turning Spoken Words into Data
Speech-to-Text (ASR) is a digital stenographer, turning spoken language into machine-readable text. It's the engine behind voice assistants, automated call routing, and video captioning.
Multimodal Models: Beyond Just Text
A multimodal model understands the world by connecting different data types, like images and text, instead of just one. It's how AI generates images from descriptions or answers questions about a photo. The footgun is assuming more data types always helps.
Multi-Agent Systems: A Team of AIs, Not a Monolith
Instead of one giant AI, a Multi-Agent System is a team of specialized AIs that collaborate on a complex problem. This appears in LLM-powered coding assistants and complex simulations.
Get AI bites daily.
Five a day, five minutes, offline. With quizzes so it sticks.
Open testing — you’ll join as an early tester.