Artificial Intelligence
Notes on AI that go past the demo: how the models work, where they break, and what changes once you put them in production.
Articles
Why Does AI Keep Hallucinating? Meet JEPA, the AI Brain With Common Sense
Generative AI hallucinates because all it does is guess word patterns. JEPA tries to change that by teaching machines how the real world works, the way a human brain does.
LLMs Are Going to Hit a Wall. What Then?
LLMs like ChatGPT are great at stringing words together, but they never really grasp reality. Yann LeCun says this architecture will hit a wall and needs a new answer.
Meet JEPA: Where AI Starts Learning Common Sense
AI hallucinates because it only guesses data probabilities without understanding reality. The JEPA architecture tries to change that by building a world model in its head.
Beyond Generative AI: JEPA Chases Human-Style Conceptual Understanding
AI usually only guesses pixels, while JEPA tries to learn from abstract concepts in latent space. That approach turns out to reach as far as reading brain waves.
Inside JEPA's Kitchen: The Secrets of EMA, VICReg, and Compute Efficiency
Bored of AI that only guesses words or memorizes pixels? Meet JEPA, an architecture that teaches machines common sense very cheaply. Here is a look at its technical insides.
MCP, Rebuilt: Good News If You're Tired of Writing Connectors
You have a few internal APIs and one AI agent, but the code has to be rewritten every time the model changes. MCP ends that, and this year the protocol was rebuilt so servers can run like ordinary web servers. Here's what changed. 🔧
AI Agent Memory: From Vector Store to Temporal Graph
Two contradictory facts make an agent answer nonsense. Here is how a vector store and a temporal knowledge graph differ at keeping long-term state.
Why RAG That Leans on Cosine Similarity Alone Keeps Missing
RAG that leans only on embeddings returns chunks that look close in meaning, not the ones you need. Here is why, and the two layers that patch it.
Linear or Graph: How to Run Many Agents Without an Eternal Loop
One agent with twenty tools gets messy fast. Once several agents revise each other, you need a graph that allows cycles and a number that makes it stop.
So Your RAG Stops Hitting 504: Split the Query Path From Ingestion
One RAG service that both parses uploads and answers queries will fall over the moment someone uploads a 200-page PDF. The cure is two paths and one queue.
Your Stream Dies at 125 Seconds and Nothing in Your Code Says 125
Streaming moves the wait into a connection that outlives the request. Four layers sit between the model and the browser, their idle timeouts disagree, and the smallest one ends your stream.
Caching That Never Hits Costs More Than No Caching
Same model, same conversation, same token count, and a bill five times higher. The cause is a prefix that changes, a write premium nobody reads about, and a cost curve that grows faster than the loop.
What a Prompt Cache Actually Remembers
Four providers cache the same bytes under four different rulebooks. The question that decides your bill: when the second request is longer than the first, does it reuse the whole prefix or only the part that was already written?