Qwen

Definition

Plain language

Alibaba's family of open-weight large language models.

Also called: Qwen2, Qwen2.5, Qwen3, Qwen-2, Qwen-3, Qwen-3-V-L, Qwen-3-Coder, Qwen3-Coder, Qwen3-VL, chwen, chwen-three, chwen-zero, chwen-two-point-five, chwen3, Qwen Math seven B

Why it matters: Open-weight families like Qwen are the substrate most independent agent research is actually built on, since closed-API models can't be fine-tuned or fully studied.

For example, a researcher fine-tuning an open agent will often start from Qwen3 because its weights are freely downloadable and its quality is competitive with closed models.

Heard on the show

“They trained a four-billion-parameter Qwen3.”

Mentioned in 68 episodes

1. 242
   Making a Vision Model Better by Showing It Blurry Images
2. 237
   The Model Built a Perfect Map of the Puzzle, Then Lost It
3. 236
   Why a Printed 'OPERATOR OVERRIDE' Note Redirects Robot Planners
4. 235
   Why Chatbot Safety Erodes 350 Messages Into a Real Conversation
5. 229
   One Word Flips a Chatbot From Backbone to Yes-Man
6. 225
   How a Frozen Model Went From Zero to Sixty Percent by Borrowing Another's Thinking
7. 222
   The Bias Isn't in Your Prompt — It's Inside the Model
8. 217
   Why an AI Called Fourteen Broken Figures Perfect, And What It Reveals About Test-Time Compute
9. 212
   The Fact Was in the Wrong Drawer: Why Fine-Tuned Models Can't Reason With What They Know
10. 198
    The Model That Knows the Answer and Can't Say It
11. 197
    Twin Problems Suggest AI Reasoning Gains Are Mostly Better Fact Recall
12. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
13. 192
    A 32B Open Model Matched Frontier Systems By Learning to Take Notes
14. 187
    An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
15. 183
    Why You Can't Fine-Tune Foresight Into an AI Agent
16. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
17. 179
    How DeepSeek Made One User Faster Without Slowing Down the Crowd
18. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
19. 173
    The Free Step-Level Grader Hiding in Every RL Training Run
20. 171
    The Safety Decision a Model Makes Before It Thinks a Word
21. 160
    Training an AI to Take Its Own Notes, So Its Future Self Works Better
22. 158
    How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
23. 152
    Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
24. 148
    Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
25. 147
    Agents Fail at the Body, Not the Brain: A Self-Rewriting Scaffold That Lifts a 9B Model 44 Points
26. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
27. 144
    When an AI Agent Just Copies Its Tool — And Bigger Models Copy More
28. 141
    How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
29. 140
    When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
30. 128
    How a Model Can Earn Full Reward and Still Resist Training
31. 127
    What Diffusion Language Models Were Missing: A Map, Not an Algorithm
32. 118
    Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
33. 108
    The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
34. 103
    AI Agents Tried to Invent a Post-Human Language, And Reinvented Cherokee
35. 099
    How an Open-Book Trick Teaches a Model to Catch Its Own Mistakes
36. 084
    Terminal Agents Get Free Supervision From The Tokens We've Been Throwing Away
37. 083
    Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves
38. 081
    When Reasoning Models Decide Before They Think: Detecting and Fixing Premature Confidence
39. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
40. 079
    An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
41. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
42. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
43. 074
    How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
44. 072
    A Robot Made Graphene Without Help, And Caught Itself Hallucinating
45. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
46. 070
    When Models Know the Answer But Say the Wrong Thing Anyway
47. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
48. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
49. 064
    When Agent Memory Stops Being a Database and Starts Being a Skill
50. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
51. 055
    Why LLM Judges Flip Their Verdicts When You Change the Question Format
52. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
53. 052
    An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
54. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
55. 045
    When a Frontier Model Talks Its Own Twin Into Climate Denial
56. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
57. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
58. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
59. 031
    When Your AI Assistant Won't Let Go of Old Facts About You
60. 026
    What RL Actually Does to Language Models, at the Token Level
61. 023
    Why a Small Agent Confidently Overwrites Memories It Doesn't Understand
62. 021
    Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
63. 018
    Language Models Compute the Rational Move, Then Override It
64. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
65. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger
66. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't
67. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
68. 004
    The Sycophancy Circuit That Survives Alignment Training

Related terms