Category: Blog

The Simple Question That Breaks AI
Three years ago, John was 30.What’s his age today?
Ask a 5-year-old, and you’ll get a confident “33.”Ask a cutting-edge LLM? You might hear, “John is still 30.”
That’s not a joke. I ran this prompt through multiple local models, including Cogito 3B and a couple of community-favorite LLMs. Two froze mid-reasoning. One hallucinated. Another confidently clung to “30” as if time itself had paused for John Smith. I had to force stop the models before they spiraled into existential loops.
That’s when I stumbled upon Apple’s quietly released research:“Reasoning in Large Language Models: A Structural Examination of LRMs”
This wasn’t just a paper. It was a mirror held up to our collective AI hype.

Apple’s Quiet Bombshell
The research doesn’t scream headlines. But if you read between the lines, the message is brutal:

Large Reasoning Models (LRMs) aren’t reasoning. They’re rehearsing — and they stumble once the stage changes.

Apple’s team didn’t just test for final answer accuracy (the usual game of solving math or code questions). Instead, they controlled compositional complexity — adjusting the logic of puzzles while holding structure steady. This allowed them to peer inside the how, not just the what.
The findings?
1. Reasoning collapses at complexity: As puzzles grow more layered, models hit a point where thinking efforts don’t rise — they shrink. The AI starts doing less when asked for more.
2. Surprising underdogs: On simple tasks, old-school LLMs (with no fancy reasoning prompts) often outperformed the so-called smarter LRMs. Because brute fluency > half-baked logic.
3. Three-tiered failure curve:

Simple tasks → LLMs win.
Medium tasks → LRMs shine with their verbose reasoning.
Hard tasks → Both fall apart. Sometimes poetically.

4. Inconsistent computation: Models don’t follow stable algorithms. Ask them to solve similar puzzles with tiny differences? Expect wildly different approaches. Like solving one with algebra and the next with vibes.

My John Smith Moment
I didn’t need a research lab to feel this.
I asked a 3B LLM to solve:“John was 30 years old 3 years ago. What’s his age now?”
First response:

“John is 30.”

Second response:

“John is still 30 because 3 years ago, he was 30.”

No reasoning. Just repetition.It was like watching a parrot misquote Socrates.
I added a prompt to “think step-by-step.”It generated a four-line explanation — all correct-sounding — ending again with: “John is 30.”
In other words, the reasoning trace sounded intelligent but led nowhere.
Apple’s paper helped me decode this:These models simulate reasoning — they don’t execute it.

So What Do We Do With This?
If you’re a leader relying on LLMs for decision-support, this should be your wake-up call.
The future of AI isn’t just in scaling up — it’s in slowing down.Tracing how a model thinks. Catching the wrong steps before they become decisions.
Right now, we’re betting billions on models that sound wise — but can’t age John by three years.

Final Thought: Are We Building Thinkers or Talkers?
The next time you hear an LLM explain something with confidence, pause.Ask yourself: Is it thinking? Or just echoing the patterns of people who once did?
And if John’s still 30 in that world — maybe we’re the ones who need to grow up.

Key Takeaways

Apple’s research reveals that Large Reasoning Models simulate rather than execute true reasoning
Simple arithmetic problems expose fundamental flaws in AI reasoning capabilities
Complexity scaling shows inverse relationship between task difficulty and model performance
Business leaders should implement reasoning verification systems before relying on AI decisions
The AI industry needs to focus on reasoning quality, not just conversational fluency

Want to stay updated on AI reasoning breakthroughs and failures? Follow for more insights on the reality behind the AI hype.

Welcome back.
In the previous post, we explored what AI agents are and why

Welcome back.

In the previous post, we explored what AI agents are and why they matter more than ever. Now, let’s open the black box and see how these agents think, plan, and act.

Spoiler: they don’t just follow instructions — they reason like humans. And sometimes better.

ReAct: Reason, Act, Reflect

ReAct (Reasoning and Action) is a framework that lets AI agents think, act, and observe in a loop.

How it works:

The agent receives a user prompt.
It reasons step-by-step — articulating its thought process.
It takes an action (e.g., calling a tool).
It observes the result.
Based on the result, it reasons again and updates its plan.

This iterative loop is like a human solving a puzzle — experimenting, reflecting, and refining.

Why it matters:

• It supports complex, unpredictable tasks.
• It’s transparent — you see the agent’s reasoning in real time.
• It helps debug or retrain the agent more easily.

ReWOO: Plan Once, Act Smart

ReWOO (Reasoning Without Observation) takes a different approach.

Instead of reacting after every step, the agent plans everything upfront, executes in bulk, and evaluates at the end.

Workflow:

The agent anticipates what tools and data it will need.
It collects everything it needs at once.
It combines the results and delivers a final output.

Why it matters:

• Faster execution.
• Less computational cost.
• Reduces risk from tool failure or API rate limits.
• More aligned with enterprise-scale, multi-tool workflows.

Types of AI Agents: From Reflex to Learning

Not every agent is built the same. Here’s a hierarchy — from simplest to most advanced:

1. Simple Reflex Agents

Hard-coded rules. No learning or context memory.

2. Model-Based Reflex Agents

Can track some internal state for better decisions.

3. Goal-Based Agents

Plan actions based on goals, not just rules.

4. Utility-Based Agents

Optimize based on outcomes and tradeoffs.

5. Learning Agents

Improve continuously with feedback, experience, or user interaction.

Why This Matters for You

If you’re still deploying bots or assistants in your workflows, you’re solving today’s problems with yesterday’s tools.

AI agents are:

• Smarter than bots.
• More independent than assistants.
• More scalable than human teams.

Whether you’re automating HR processes, sales reports, IT tickets, or customer service — agents are the next layer of business performance.

Final Thought

When software starts thinking, planning, and executing on your behalf — your role changes from operator to orchestrator.

So ask yourself:

Are you building tools? Or are you assembling agents?

Because those who build agents now… …won’t be building slide decks later.

Related: Read Part 1: What Are AI Agents? And Why They’re Not Just Fancy Chatbots to understand the fundamentals of AI agents.