Techniques for Better Decision Making

I’ve never had two editorials in top-tier journals focused on the same paper. It’s flattering, of course — even a pig blushes when praised, as Yattaman once wrote. But what really struck me about the PNAS commentary is something else: it got the point. Not the easy one. Not the marketable one. Not the usual talk about “how good” or “how human” or “how enabling” these systems are. The real question is more uncomfortable: if the promise is delegation, how do LLMs actually construct a judgment? Our work is not about accuracy. It is about architecture. Not what they answer, but how answers are produced. And when you look at that closely, the illusion of equivalence collapses. Humans and models may produce similar sentences, similar ratings, similar decisions — but they do not get there through the same cognitive structure. And this is not a technical detail. It’s an ontological fracture. Human judgment is embodied. It emerges from experience, memory, emotion, context, intention. It is grounded in a life. LLM “judgment” is not. It has no experience, no time, no world. It operates on statistical regularities among symbols, not on events in reality. And yet — this is the trap — the outputs can look the same. When radically different processes generate indistinguishable language, the problem is no longer technological. It becomes epistemological. This is what we call Epistemia: the moment when linguistic plausibility starts replacing verification, and the form of knowledge substitutes for the labor of knowing. Not because models lie — but because they simulate judgment so well that we forget what judgment actually is. https://lnkd.in/dcu7cuZm

You know all those arguments that LLMs think like humans? Turns out it's not true 😱 In our new paper we put this to the test by checking if LLMs form concepts the same way humans do. Do LLMs truly grasp concepts and meaning analogously to humans, or is their success primarily rooted in sophisticated statistical pattern matching over vast datasets? We used classic cognitive experiments as benchmarks. What we found is surprising... 🧐 We used seminal datasets from cognitive psychology that mapped how humans actually categorize things like "birds" or "furniture" ('robin' as a typical bird). The nice thing about these datasets is that they are not crowdsourced, they're rigorous scientific benchmarks. We tested 30+ LLMs (BERT, Llama, Gemma, Qwen, etc.) using an information-theoretic framework that measures the trade-off between: - Compression (how efficiently you organize info) - Meaning preservation (how much semantic detail you keep) Finding #1: The Good News LLMs DO form broad conceptual categories that align with humans significantly above chance. Surprisingly (or not?), smaller encoder models like BERT outperformed much larger models. Scale isn't everything! Finding #2: But LLMs struggle with fine-grained semantic distinctions. They can't capture "typicality" - like knowing a robin is a more typical bird than a penguin. Their internal concept structure doesn't match human intuitions about category membership. Finding #3: The Big Difference Here's the kicker: LLMs and humans optimize for completely different things. - LLMs: Aggressive statistical compression (minimize redundancy) - Humans: Adaptive richness (preserve flexibility and context) This explains why LLMs can be simultaneously impressive AND miss obvious human-like reasoning. They're not broken - they're just optimized for pattern matching rather than the rich, contextual understanding humans use. What this means: - Current scaling might not lead to human-like understanding - We need architectures that balance compression with semantic richness - The path to AGI ( 😅 ) might require rethinking optimization objectives Our paper gives tools to measure this compression-meaning trade-off. This could guide future AI development toward more human-aligned conceptual representations. Cool to see cognitive psychology and AI research coming together! Thanks to Chen Shani, Ph.D., who did all the work and Yann LeCun and Dan Jurafsky for their guidance

Making effective product decisions and securing the necessary buy-in can be hard. Imagine that you are running a product roadmapping workshop to which you’ve invited the key stakeholders and development team members. At the end of the session, you ask, “Is everybody OK with the roadmap changes?” As nobody says anything, you assume that everyone agrees, and you close the meeting. But in reality, most people are still thinking about the changes proposed. To make things worse, it’s not clear who has the final say on the roadmap changes. Is it you, the person in charge of the product, everyone attending the workshop, or the management sponsor? But if you want people to move forward together, they must understand who decides and if a decision has been made. In my latest video, I explain how you can achieve this by using the right decision rule. Here are the five rules I discuss: 1️⃣ Unanimity: Everyone required to make a decision agrees with the proposed solution and is happy to support it. Great for setting the product vision and creating a new product strategy. 2️⃣ Consent: Nobody disapproves or objects. Helpful for making product roadmapping decisions like the one in the scenario above. 3️⃣ Majority Vote: More than half of the people vote for the proposal. Suitable for lower-impact decisions such as setting a sprint goal. 4️⃣ Product Person Decides after Discussion: The person in charge of the product makes the decision after an open discussion. Beneficial when a decision must be made quickly, for example, in an emergency. 5️⃣ Delegation: You empower others to decide, for instance, a cross-functional development team to make UX design and technical decisions. Hope you'll find the video helpful! #productmanagement #decisionmaking #innovation #stakeholdermanagement #decisionrules

I've coached 400+ CEOs. The best ones don't communicate better. They communicate differently. While average leaders wing it, great ones use proven methods that turn conversations into opportunities. After 20+ years studying top performers, I've identified 7 communication systems that separate good from great. (Save this. You'll need it for your next big meeting.) 1. The 3 Levels of Listening Stop listening to reply. Start listening to understand. Level 1: You're thinking about your response Level 2: You're focused on their words Level 3: You're reading the room—energy, tone, silence One CEO used this to uncover why his top performer was really leaving. Saved a $10M account. 2. What? So What? Now What? Transform rambling updates into decisive action. What = The facts (30 seconds max) So What = Why it matters to the business Now What = The specific decision needed Cut meeting time by 40%. 3. PREP Method Never fumble another investor question. Point: Your answer in one sentence Reason: Why you believe it Example: Proof from your business Point: Reinforce your answer Practice this for 5 minutes daily. Sound prepared always. 4. RACI Matrix Kill confusion before it starts. Responsible: Who does the work Accountable: Who owns success/failure (only ONE person) Consulted: Who gives input Informed: Who needs updates Projects with clear RACI are 3x more likely to succeed. 5. Story of Self/Us/Now Move hearts, not just minds. Story of Self: Why YOU care (personal conviction) Story of Us: Our shared challenge Story of Now: The urgent choice we face This framework has helped politicians win. It'll help you raise capital or inspire your team to meet a big goal. 6. The Pyramid Principle Get board approval in half the time. Start with your recommendation Give 3 supporting arguments (max) Order by impact (strongest first) Data goes last, not first McKinsey consultants swear by this. So should you. 7. COIN Feedback Model Make tough conversations productive. Context: When and where it happened Observation: What you saw (facts only) Impact: The business consequence Next: Agreed action steps No more avoided conversations. No more resentment. Your next funding round, key hire, or major deal doesn't depend on working harder. It depends on communicating better. Because in the end, leadership isn't about having all the answers. It's about asking better questions, listening deeper, and communicating with precision. Your team is waiting for you to lead like this. P.S. Want a PDF of my Leadership Communication Cheat Sheet? Get it free: https://lnkd.in/dQUbS7A6 ♻️ Repost to help a founder level up their communication. Follow Eric Partaker for more leadership tools. —— 📢 Want to become a world-class CEO? I'm hosting a FREE LIVE TRAINING: "Build Your Business By Networking" Wed, Nov 5, 12:30pm Eastern / 5:30pm UK https://lnkd.in/d7be8hBY

One of the biggest challenges I see with scaling LLM agents isn’t the model itself. It’s context. Agents break down not because they “can’t think” but because they lose track of what’s happened, what’s been decided, and why. Here’s the pattern I notice: 👉 For short tasks, things work fine. The agent remembers the conversation so far, does its subtasks, and pulls everything together reliably. 👉 But the moment the task gets longer, the context window fills up, and the agent starts forgetting key decisions. That’s when results become inconsistent, and trust breaks down. That’s where Context Engineering comes in. 🔑 Principle 1: Share Full Context, Not Just Results Reliability starts with transparency. If an agent only shares the final outputs of subtasks, the decision-making trail is lost. That makes it impossible to debug or reproduce. You need the full trace, not just the answer. 🔑 Principle 2: Every Action Is an Implicit Decision Every step in a workflow isn’t just “doing the work”, it’s making a decision. And if those decisions conflict because context was lost along the way, you end up with unreliable results. ✨ The Solution to this is "Engineer Smarter Context" It’s not about dumping more history into the next step. It’s about carrying forward the right pieces of context: → Summarize the messy details into something digestible. → Keep the key decisions and turning points visible. → Drop the noise that doesn’t matter. When you do this well, agents can finally handle longer, more complex workflows without falling apart. Reliability doesn’t come from bigger context windows. It comes from smarter context windows. 〰️〰️〰️ Follow me (Aishwarya Srinivasan) for more AI insight and subscribe to my Substack to find more in-depth blogs and weekly updates in AI: https://lnkd.in/dpBNr6Jg

I became a VP at Amazon because I made some risky bets and got them right. I also had some go wrong. But because I generally made good decisions quickly and minimized the risks, I won enough to move up. Here is how you can learn this essential executive skill: The first piece is understanding that the idea of making the “right decision” is a fallacy. Choices in business are not between right and wrong or good and bad options. In fact, they are usually between multiple potentially good options. This truth becomes an obstacle for leaders because they often wait for one option to present itself as superior, but this clarity never comes (or it comes far too late). This is why Jeff Bezos says that you should make your decisions with 70% of the desired data or information. If you wait for 100%, you will either never make a decision or you will make it too late to benefit from it. As a leader, you must become comfortable with making decisions that you don’t *know* are correct. Second, so that your quick decisions aren’t reckless, you must understand the pieces of making an uncertain decision. There are three pieces of every decision to consider: 1) How confident you are in your choice. Remember, this will almost never be 100%. 2) How costly it would be to be wrong. 3) The cost of delaying your decision. Weighing these three factors together will give you a matrix of how to decide—the higher the consequences, the more confidence you need; the higher the cost of delay, the faster you need to move. Finally, you must understand the cost and time commitment of undoing your choice. This should be part of your cost analysis in question two above, and it is also the root of Jeff Bezos’s “One-way and Two-way Doors” theory. Basically, if you know that each decision you make will potentially need to be undone, you must think through that process. For things that are easily rolled back or fixed, move quickly. For actions that are difficult to undo or erase, take more time to build confidence and mitigate risk. If you use these three ideas to build a personal decision-making system, you will be able to quickly make impactful decisions with a high percentage of accuracy, and you will be able to clean up the mess left when you get it wrong. Being right a lot (an Amazon LP), iterating quickly, and being able to do damage control will get you very far as a leader. On the other hand, waiting to make perfect decisions will keep you stuck. If you want to learn more about high speed decision-making systems, read this week’s newsletter: https://buff.ly/mevN6RJ I will be writing more about this topic in the coming weeks, so make sure to subscribe if you are interested.

We’ve all seen variations of this comic on LinkedIn. They’re “funny” — but they also show a problem: we’re using AI with an old, document-centric mindset. Five bullets → AI inflates to 12 pages → AI compresses back to five bullets. That’s not intelligence; it’s content ping-pong. We’re optimizing for length, not for decisions. A better way: in a case like this, AI should act as a decision co-pilot, not a text generator. Instead of “write 12 pages,” ask AI to: 1. Clarify intent & audience. “What decision must be made, by whom, and by when?” 2. Build a 1-page Decision Brief: recommendation, three supporting reasons, risks/mitigations, options considered, next steps. 3. Link evidence, don’t paste it: connect to the data and surface the few charts or numbers that matter. 4. Generate fit-for-purpose outputs: • exec email (≤200 words with clear ask) • one-slide visual for the meeting • optional appendix with traceable sources 5. Push back when inputs are weak: ask for gaps, assumptions, and thresholds that would change the recommendation. 6. Automate the loop: monitor the underlying data and update the brief if something material changes. Try this prompt: “Turn these 5 bullets into a 1-page Decision Brief for [audience]. State the recommended action, key reasons, risks, alternatives, and next steps. Produce: (a) a 200-word exec email with a clear decision request, (b) a single summary slide, and (c) links to supporting data. Ask me any clarifying questions first.” Write less. Decide faster. Deliver clarity. #AI #AgenticAI #DecisionIntelligence #Productivity #FutureOfWork #Leadership #Communication

I was Wrong about Influence. Early in my career, I believed influence in a decision-making meeting was the direct outcome of a strong artifact presented and the ensuing discussion. However, with more leadership experience, I have come to realize that while these are important, there is something far more important at play. Influence, for a given decision, largely happens outside of and before decision-making meetings. Here's my 3 step approach you can follow to maximize your influence: (#3 is often missed yet most important) 1. Obsess over Knowing your Audience Why: Understanding your audience in-depth allows you to tailor your communication, approach and positioning. How: ↳ Research their backgrounds, how they think, what their goals are etc. ↳ Attend other meetings where they are present to learn about their priorities, how they think and what questions they ask. Take note of the topics that energize them or cause concern. ↳ Engage with others who frequently interact with them to gain additional insights. Ask about their preferences, hot buttons, and any subtle cues that could be useful in understanding their perspective. 2. Tailor your Communication Why: This ensures that your message is not just heard but also understood and valued. How: ↳ Seek inspiration from existing artifacts and pickup queues on terminologies, context and background on the give topic. ↳ Reflect on their goals and priorities, and integrate these elements into your communication. For instance, if they prioritize efficiency, highlight how your proposal enhances productivity. ↳Ask yourself "So what?" or "Why should they care" as a litmus test for relatability of your proposal. 3. Pre-socialize for support Why: It allows you to refine your approach, address potential objections, and build a coalition of support (ahead of and during the meeting). How: ↳ Schedule informal discussions or small group meetings with key stakeholders or their team members to discuss your idea(s). A casual coffee or a brief virtual call can be effective. Lead with curiosity vs. an intent to respond. ↳ Ask targeted questions to gather feedback and gauge reactions to your ideas. Examples: What are your initial thoughts on this draft proposal? What challenges do you foresee with this approach? How does this align with our current priorities? ↳ Acknowledge, incorporate and highlight the insights from these pre-meetings into the main meeting, treating them as an integral part of the decision-making process. What would you add? PS: BONUS - Following these steps also expands your understanding of the business and your internal network - both of which make you more effective. --- Follow me, tap the (🔔) Omar Halabieh for daily Leadership and Career posts.

In high-stakes decisions, “right” and “wrong” aren’t the point. Your method for making decisions matters more than any single result. Every major choice is a bet on a particular future. Decision quality and outcome quality are two entirely different things. Our brains want tidy stories, so we judge a decision’s quality by its outcome — a bias known as resulting. A brilliant process can still produce a bad outcome because of one unlucky break. Pete Carroll’s infamous Super Bowl call to pass from the 1-yard line was statistically sound, yet it’s reviled because it ended in a game-losing interception. To escape the trap of resulting, you need a better process. The world’s best venture capitalists use repeatable frameworks that protect them from bias and focus their attention where it matters most. Their playbook starts with two disciplines: 𝟭. 𝗦𝗼𝗿𝘁 𝘆𝗼𝘂𝗿 𝗱𝗲𝗰𝗶𝘀𝗶𝗼𝗻𝘀: 𝗢𝗻𝗲-𝗪𝗮𝘆 𝘃𝘀. 𝗧𝘄𝗼-𝗪𝗮𝘆 𝗗𝗼𝗼𝗿𝘀 Jeff Bezos uses this mental model to allocate energy: “Two-way doors” are reversible — make those decisions quickly quickly. “One-way doors” are consequential and nearly irreversible, so you should take them slow and deliberate. The first step to better decisions is knowing which door you’re facing. 𝟮. 𝗛𝘂𝗻𝘁 𝗳𝗼𝗿 𝗮𝘀𝘆𝗺𝗺𝗲𝘁𝗿𝗶𝗰 𝗯𝗲𝘁𝘀 Stop worrying about avoiding failure and start making sure your wins are big enough to make failures irrelevant. Don’t just assess the most likely outcome. Map the full range of possibilities. A bet with a 70% chance of a small loss but a 10% chance of a 100x return can be a career-defining win. Top VCs know they’ll be wrong most of the time. In fact, they’re not aiming to be right every time. They’re looking for situations where the upside of a win is exponentially larger than the downside of a loss. I’ll be diving deeper into the methodology behind high-quality decisions in my fall Maven cohort. It’s designed for entrepreneurs, investors, and exec decision makers who have to make dozens of decisions each day. Every decision is a bet on a forecast of the future. You have limited resources to figure out which prediction will have the best return in the long run. In my course, I’ll cover my 6-step process for better, faster decision making: https://bit.ly/4ljImns

𝐓𝐡𝐨𝐬𝐞 𝐖𝐡𝐨 𝐓𝐫𝐲 𝐉𝐮𝐠𝐠𝐥𝐢𝐧𝐠 𝐓𝐨𝐨 𝐌𝐚𝐧𝐲 𝐁𝐚𝐥𝐥𝐬 𝐅𝐚𝐢𝐥 𝐌𝐢𝐬𝐞𝐫𝐚𝐛𝐥𝐲. You’re juggling three balls, it feels you’ve got this. Now you’re juggling four, it’s tough but you manage. Now you’re juggling five, chaos builds. Now you’re juggling six, you drop all of them! That’s exactly how cognitive load feels. When your brain is juggling too much information and too many decisions at the same time. As a psychologist, I see this all the time. People think they’re indecisive or unproductive, but the truth is, their mental bandwidth is maxed out. 𝐂𝐨𝐠𝐧𝐢𝐭𝐢𝐯𝐞 𝐥𝐨𝐚𝐝 - 𝐭𝐡𝐞 𝐦𝐞𝐧𝐭𝐚𝐥 𝐰𝐞𝐢𝐠𝐡𝐭 𝐨𝐟 𝐩𝐫𝐨𝐜𝐞𝐬𝐬𝐢𝐧𝐠 𝐭𝐨𝐨 𝐦𝐮𝐜𝐡 𝐢𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 𝐢𝐬 𝐨𝐧𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐛𝐢𝐠𝐠𝐞𝐬𝐭 𝐛𝐚𝐫𝐫𝐢𝐞𝐫𝐬 𝐭𝐨 𝐜𝐥𝐞𝐚𝐫, 𝐜𝐨𝐧𝐟𝐢𝐝𝐞𝐧𝐭 𝐝𝐞𝐜𝐢𝐬𝐢𝐨𝐧-𝐦𝐚𝐤𝐢𝐧𝐠. When your brain is overwhelmed, even small decisions feel monumental. That’s why you might spend ages picking a restaurant after a day of big meetings. Your brain isn’t lazy—it’s overworked. But it’s not just about feeling tired. Cognitive load impacts the quality of your decisions. The more overwhelmed you are, the more likely you are to choose what’s easy, familiar, or convenient, not necessarily what’s best. Sounds scary. Right? I’ve worked with clients who felt stuck, unable to decide between career moves, new opportunities, or even personal goals. Most of the time, the problem wasn’t indecision. It was the sheer amount of information and options clouding their minds. 𝐒𝐨, 𝐡𝐨𝐰 𝐝𝐨 𝐲𝐨𝐮 𝐥𝐢𝐠𝐡𝐭𝐞𝐧 𝐭𝐡𝐞 𝐦𝐞𝐧𝐭𝐚𝐥 𝐥𝐨𝐚𝐝 𝐚𝐧𝐝 𝐦𝐚𝐤𝐞 𝐛𝐞𝐭𝐭𝐞𝐫 𝐝𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬? → 𝐋𝐢𝐦𝐢𝐭 𝐘𝐨𝐮𝐫 𝐈𝐧𝐩𝐮𝐭𝐬: Be selective about what you consume. Your brain wasn’t designed to process infinite notifications or social feeds. Filter and focus. → 𝐁𝐚𝐭𝐜𝐡 𝐒𝐢𝐦𝐢𝐥𝐚𝐫 𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬: Make decisions in clusters. Planning your week’s meals in one go is far less taxing than deciding every day. → 𝐒𝐞𝐭 𝐁𝐨𝐮𝐧𝐝𝐚𝐫𝐢𝐞𝐬: Not every choice deserves endless time. Give yourself limits. Trust your instincts and move forward. One client came to me overwhelmed by decisions, from strategic career moves to daily operations. We simplified her processes, grouped her tasks, and gave her decision-making space. Within weeks, she felt clearer, more confident, and far more in control. Cognitive load isn’t something you can escape entirely, but you can manage it. By reducing the mental clutter, you create space for clarity, confidence, and focus. If this clicks with you, I’d be delighted to share more insights into the psychology of decision-making with your team! Let’s get talking! #decisionmaking #team #mentalhealth #career #psychology #personaldevelopment