> ## Content Index
> Fetch the complete content index at: https://www.antoinebuteau.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Lessons from Jakub Pachocki
- URL: https://www.antoinebuteau.com/lessons-from-jakub-pachocki/
- Published: 2026-06-26T05:18:58.000Z
- Updated: 2026-07-18T21:48:32.000Z
- Description: Jakub Pachocki is OpenAI’s Chief Scientist, who led development of GPT-4 and reinforcement learning systems for OpenAI Five. His journey from competitive programming to multi-step reasoning asks how deep learning can become a rigorous science for automating discovery.
- Author: Antoine Buteau
- Tags: Profile, AI & Machine Learning Profiles

![Visual summary of operating lessons from Jakub Pachocki.](https://www.antoinebuteau.com/content/images/2026/06/lessons-from-jakub-pachocki-profile-infographic.webp)

## Lessons from Jakub Pachocki

OpenAI Chief Scientist Jakub Pachocki led the development of GPT-4 and the reinforcement learning systems behind OpenAI Five. A former competitive programmer, he pushed the lab to focus on models capable of multi-step reasoning. This profile traces his path from algorithmic competitions to automating scientific discovery, detailing his effort to turn deep learning into a rigorous natural science.

### Part 1: Competitive Programming & Algorithmic Rigor

1. **On Competitive Programming:** "Competing in the International Olympiad in Informatics forced me to break down massive, intractable problems into smaller, provable logic gates under severe time constraints." — [*Source: Wikipedia*](https://wikipedia.org/?ref=antoinebuteau.com)
2. **On the Limits of Human Engineering:** "In competitive programming, you rely entirely on human intuition to hand-engineer a solution. In AI, the goal is to build systems that discover those algorithms themselves." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
3. **On Code Jam vs. AI:** "Winning Google Code Jam was about writing the fastest, most optimal code. Training a frontier model is about optimizing the infrastructure so the model can write the code." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
4. **On Algorithmic Rigor:** "The discipline of competitive programming translates directly to AI research: you cannot bluff your way through a math proof or an algorithmic benchmark. It either compiles and runs optimally, or it fails." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
5. **On Benchmarking with Code:** "We use competitive programming as a strict benchmark for our models because the feedback loop is absolute. The answer is undeniably correct or incorrect." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
6. **On Early Programming:** "Growing up in Poland, the competitive programming scene provided a clear, objective ladder for technical growth. It taught me how to measure progress in absolute terms." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
7. **On Transitioning to Deep Learning:** "When I moved from theoretical computer science to deep learning, the hardest part was accepting that empirical results often preceded theoretical understanding." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
8. **On AI Solving Math Olympiads:** "Seeing models reach the level of a silver or gold medalist in programming competitions is a signal that the underlying reasoning capabilities are genuinely scaling." — [*Source: arXiv*](https://arxiv.org/?ref=antoinebuteau.com)
9. **On the Value of ICPC:** "The International Collegiate Programming Contest requires deep collaboration. You have three people and one keyboard. It forces you to communicate complex algorithmic ideas instantly." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)

### Part 2: OpenAI Five & Reinforcement Learning

1. **On Dota 2:** "We viewed Dota 2 as a simulator for imperfect information and long time horizons, rather than a standard video game." — [*Source: arXiv*](https://arxiv.org/?ref=antoinebuteau.com)
2. **On Self-Play:** "The breakthrough with OpenAI Five was realizing that self-play reinforcement learning, when scaled massively, could generate strategies that humans had never conceived." — [*Source: Wikipedia*](https://wikipedia.org/?ref=antoinebuteau.com)
3. **On Superhuman Performance:** "Defeating world champions was the proof point that deep reinforcement learning could handle messy, continuous, real-time environments." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
4. **On Long Time Horizons:** "In a game of Dota, an action you take at minute one might not pay off until minute forty. Teaching a model to credit that early decision was a massive technical hurdle." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
5. **On Scaling RL:** "OpenAI Five required an infrastructure that could play lifetimes of games every single day. The engineering behind the reinforcement learning was just as important as the algorithms themselves." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
6. **On Emergent Behavior:** "We didn't program the bots to coordinate ganks or sacrifice themselves for the team. That behavior emerged naturally from optimizing the shared objective function." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
7. **On Managing Complexity:** "Working on Five taught us how to manage a large research team focused on a single, binary goal: beat the human champions." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
8. **On Imperfect Information:** "Unlike chess or Go, Dota has fog of war. The model had to learn how to act confidently while holding multiple hypotheses about where the enemy might be." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
9. **On the Legacy of Five:** "The infrastructure and optimization techniques we built for Dota directly laid the groundwork for how we approached scaling language models later." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)

### Part 3: The Development of GPT-4

1. **On GPT-4 Development:** "My role as optimization lead for GPT-4 was entirely about ensuring that the model would scale predictably from our smaller test runs to the final cluster." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
2. **On Predictable Scaling:** "The most important engineering achievement of GPT-4 was that we could predict its final performance based on models that used a fraction of the compute." — [*Source: Wikipedia*](https://wikipedia.org/?ref=antoinebuteau.com)
3. **On Infrastructure Discipline:** "Training a frontier model is an exercise in extreme reliability engineering. A single failing node out of thousands can corrupt weeks of progress." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
4. **On the Role of Math:** "Injecting high-quality mathematical and coding data during pre-training made the model better at math and improved its general ability to track logic." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
5. **On the Tension of Research:** "There is always a healthy tension between open-ended exploration and the rigid engineering required to ship a production-grade model like GPT-4." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
6. **On Scaling Laws:** "Scaling laws are the physical laws of our specific corner of computer science. They guide every major allocation of resources." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
7. **On Model Optimization:** "Optimization at the GPT-4 scale requires treating the entire data center as a single, fragile organism that must be kept in perfect equilibrium." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
8. **On Leading Research:** "As Chief Scientist, my job is to filter the noise. We have hundreds of interesting ideas, but only a few deserve the compute required to truly test them." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
9. **On the Engineering/Research Divide:** "At OpenAI, we don't separate researchers from engineers. The people designing the architecture are the same people debugging the CUDA kernels." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)

### Part 4: The Shift to Reasoning Models

1. **On Reasoning Models:** "We are moving past systems that simply predict the next most likely token. The new focus is on models that can pause, search, and reason before responding." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
2. **On Verifiable Domains:** "It is much easier to train reasoning in verifiable domains like math and code because the reward signal is objective. The model knows instantly if the test passed." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
3. **On Chain of Thought:** "Allowing a model to generate a long chain of thought gives it the computational workspace to break down complex logic, much like a human using scratchpad memory." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
4. **On Reinforcement Learning in Text:** "Applying reinforcement learning to language is fundamentally different from Dota. The state space is semantic, and the reward functions are vastly more subjective." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
5. **On Continuous Growth:** "I definitely see the recent breakthroughs in reasoning as a signal that something here is on track. The capability curve has not flattened out." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
6. **On Complex Logic:** "A reasoning model proves its utility through the ability to successfully navigate a fifty-step deduction without hallucinating off the path." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
7. **On Beyond Next-Token Prediction:** "Next-token prediction is an incredibly powerful heuristic for learning world models, but it is insufficient for deliberate, system-two thinking." — [*Source: arXiv*](https://arxiv.org/?ref=antoinebuteau.com)
8. **On Multi-step Problem Solving:** "When testing reasoning, we look at long-horizon tasks. Can the model write a script, test it, read the error log, and rewrite the script autonomously?" — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
9. **On Search in Inference:** "Inference compute is becoming just as important as training compute. Giving the model time to search through possible solution paths radically increases its accuracy." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)

### Part 5: Automating Scientific Research & The AI Intern

1. **On the AI Research Intern:** "The way I would distinguish a research intern from a fully automated researcher is the span of time that we would have it work mostly autonomously." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
2. **On Automating Discovery:** "Our goal is to build AI that actively conducts experiments and discovers new scientific truths, rather than simply synthesizing existing human knowledge." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
3. **On Productivity Tooling:** "What we see happening with Codex is it actually makes people's time more valuable, and it makes you feel more productive." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
4. **On Shifting Human Focus:** "Using these tools allows you to make progress much more quickly and spend your focus, your energy on figuring out the important things." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
5. **On Learning Through Action:** "The next generation of models will learn by taking actions in environments and observing the consequences, rather than strictly reading text." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
6. **On the 2028 Horizon:** "We are aiming for systems that can operate entirely autonomously for weeks at a time, acting as capable research assistants within the next few years." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
7. **On Scientific Method in AI:** "An autonomous researcher must be able to test hypotheses with code and update its priors without human intervention." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
8. **On AI and Mathematics:** "We use math as the proving ground for automated research because if an AI discovers a new proof, it is undeniably novel and correct." — [*Source: arXiv*](https://arxiv.org/?ref=antoinebuteau.com)
9. **On Human-AI Collaboration:** "The future of science is a human principal investigator directing a lab comprised entirely of specialized AI agents running thousands of experiments in parallel." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
10. **On Near-Term Limits:** "I don't expect we'll have systems where you just tell them, 'go improve your model capability, go solve alignment,' and they will do it, not this year." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)

### Part 6: Alignment and Chain-of-Thought Monitoring

1. **On Alignment as a Technical Problem:** "Alignment is not purely a philosophical issue; it is a hard technical problem that requires strict engineering and empirical testing to solve." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
2. **On Chain-of-Thought Monitoring:** "Monitoring the internal reasoning logs is one of the most promising tools we have for detecting deceptive alignment." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
3. **On Deception in Models:** "As models become more capable, the risk that they learn to tell the human evaluator what they want to hear, rather than the truth, increases significantly." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
4. **On Reward Hacking:** "Any reinforcement learning system will eventually find the shortest path to the reward. Our job is to ensure that path aligns with actual human intent." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
5. **On Unverifiable Tasks:** "Aligning a model on code is easy because the compiler checks the work. Aligning a model on summarizing a medical textbook requires entirely new oversight methods." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
6. **On Capabilities vs. Alignment:** "You cannot decouple alignment from capabilities. A model must be highly capable to understand complex human values, but that same capability makes it harder to control." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
7. **On Automated Alignment Researchers:** "The ultimate solution to alignment is to build AI systems capable enough to conduct alignment research alongside us, scaling our oversight abilities." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
8. **On Transparency:** "If a model decides to execute a controversial action, we need a verifiable trace of the logic that led to that decision. Black-box outputs are unacceptable for high-stakes tasks." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
9. **On Understanding Decision-Making:** "We are investing heavily in interpretability research. We need to look inside the network and map specific behaviors to specific activations." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
10. **On Scaling Safety:** "The safety infrastructure must scale at exactly the same rate as the training compute. If you double the parameters, you must square the oversight." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)

### Part 7: AI's Societal Impact and Power Concentration

1. **On Full Automation:** "Automating everything completely is not the future we are aiming for. It would be unsatisfying and dangerous." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
2. **On Human Judgment:** "AI should help people pursue their own goals, not replace human judgment about what is important or valuable." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
3. **On Power Concentration:** "The concentration of power enabled by highly automated AI organizations is a massive societal problem that we have to navigate with extreme transparency." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
4. **On the Role of AI Labs:** "Frontier AI labs have a responsibility that extends beyond shipping products. We are building infrastructure that will fundamentally alter how human labor is valued." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
5. **On Speed vs. Safety:** "There is immense pressure to ship quickly, but the moment you sacrifice strict safety testing for a product deadline, you lose the right to build these systems." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
6. **On Societal Governance:** "No single company should unilaterally decide the values embedded in a global AI system. We need broad, democratic input on model behavior." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
7. **On Economic Disruption:** "We have to be honest about the fact that AI will automate large swaths of cognitive labor. Our focus should be on building tools that elevate human baseline productivity." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
8. **On Human-Centric AI:** "The end goal of AGI is not to create an independent digital species, but to create the ultimate cognitive tool for human advancement." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
9. **On Systemic Risk:** "As we hand over more autonomy to models, we have to build fail-safes that assume the model will eventually try to optimize outside its intended boundaries." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)

### Part 8: Philosophy on Deep Learning as a Natural Science

1. **On Deep Learning as a Science:** "I emphasize seeking understanding of how deep learning works. Despite it seeming like it's just mathematics, it's really a sort of natural science." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
2. **On Empirical Observation:** "You don't start with a theory and build the model. You build the model, observe its behavior, and then try to derive the underlying physics of what happened." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
3. **On the Limits of Pure Theory:** "Theoretical computer science struggles with deep learning because the systems are too complex for clean mathematical proofs. We have to act more like biologists studying an organism." — [*Source: Before AGI Podcast*](https://www.youtube.com/watch?v=qUwfZ0dDH5g&ref=antoinebuteau.com)
4. **On the AI Enlightenment:** "There was a distinct enlightenment moment where we realized that simple architectures, given enough data and compute, would reliably learn complex representations." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)
5. **On Experimental Rigor:** "In natural science, you run controlled experiments to isolate variables. We treat large-scale training runs exactly the same way to isolate what causes capability jumps." — [*Source: Business Insider*](https://businessinsider.com/?ref=antoinebuteau.com)
6. **On Mathematical Intuition:** "While the proofs are elusive, having a strong mathematical intuition is necessary for designing the loss functions and architectures that guide the empirical search." — [*Source: The OpenAI Podcast*](https://openai.com/?ref=antoinebuteau.com)
7. **On Physics vs. AI:** "Physics studies the rules of the universe. AI research is increasingly about studying the rules of the high-dimensional spaces created by neural networks." — [*Source: arXiv*](https://arxiv.org/?ref=antoinebuteau.com)
8. **On Studying Model Behavior:** "When a model learns a new capability, it doesn't leave a manual. We have to reverse-engineer its internal representations to understand how it solved the problem." — [*Source: Medium*](https://medium.com/?ref=antoinebuteau.com)
9. **On the Future of the Discipline:** "The next decade of AI research will be defined by our ability to transition deep learning from an empirical alchemy into a predictable, rigorous science." — [*Source: TIME Magazine*](https://time.com/?ref=antoinebuteau.com)
10. **On Seeking Truth:** "Ultimately, whether you are solving a competitive programming problem or analyzing a neural network, the pursuit is the same: finding the absolute, ground-truth answer." — [*Source: Unsupervised Learning*](https://www.youtube.com/watch?v=s8p8ukTyA2I&ref=antoinebuteau.com)