To understand a word, a chatbot doesn't read straight ahead — it looks back at the other words and decides which ones matter most. That single trick is called attention, and it's the engine inside every modern AI. Click a word and watch it look.
Pick a sentence, then tap any word. Glowing lines shoot back to the earlier words it pays attention to — a fat, bright line means "this one really matters." The brightest target is what the word is really about.
🟡 the strongest link (what it's mostly about) 🔵 weaker links it also peeks at.
Some sentences are genuinely impossible — the answer isn't in the words. Here, who is “she”? Zoe, who told? Or Maya, who was told? Hit the button and watch attention split down the middle, unsure.
The glowing purple word is a pronoun — it stands in for something said earlier. Click the word it really points to. Solve 3 to earn your final badge.
Your tracer looks at the whole sentence at once — that's the real leap. Here's the ladder from yesterday's guesser up to a true Transformer:
Predict the next word from just the previous one or two. ✅ Tiny & fast. ⚠️ Forgets everything older — it loses the thread of who "she" or "it" was.
Weigh every earlier word and focus on the ones that matter. ✅ Catches references across the whole line. ⚠️ More words = more compute to compare.
Run many attention "looks" at once, layer them dozens deep, and give every word a meaning-vector. ✅ Powers every chatbot. ⚠️ Needs oceans of data + compute.
You cracked the trick behind every modern chatbot: to understand a word, the model looks back and decides which other words matter — that's attention. Stack it deep and you've got a Transformer. You now know the real engine inside ChatGPT.