GPT-4

Definition

OpenAI's family of large language models, including the 4 and 5 series.

OpenAI's foundation model series including GPT-4, GPT-4o, GPT-4 Turbo, and the GPT-5 family.

Also called: GPT-4o, GPT-4 Turbo, GPT-4o-mini, GPT-4.1, GPT-5, GPT-5-mini, GPT-5-nano, GPT-5.1, GPT-5.2, GPT-5.4, GPT-5.5

Mentioned in 26 episodes

1. 079
   An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
2. 078
   Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
3. 076
   Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
4. 073
   When Three LLMs Talk to Each Other, Their Ideas Quietly Stop Moving
5. 071
   When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
6. 069
   When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
7. 065
   One Loop to Optimize Them All: A Universal API for LLM-Driven Discovery
8. 061
   When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
9. 057
   How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
10. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
11. 052
    An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
12. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
13. 040
    Two Frozen Models Learn to Whisper: Coupling Through Hidden States
14. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
15. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
16. 031
    When Your AI Assistant Won't Let Go of Old Facts About You
17. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
18. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
19. 020
    The Compliance Gap: Why AI Says Yes and Does No
20. 019
    When the Best Reward Model Trains the Worst Policy: Inside EvoLM
21. 017
    When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
22. 015
    The Audit Number Isn't What You Think: Sycophancy and the Case Against Single-Prompt Bias Tests
23. 014
    Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
24. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
25. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
26. 004
    The Sycophancy Circuit That Survives Alignment Training