Llama

Definition

Plain language

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

Also called: Llama-2, Llama-3, Llama-3.1, Llama-3.3, Llama-4

Why it matters: The Llama family is a backbone of open AI research, so its capabilities and licensing terms shape what independent labs and startups can build.

For example, a researcher might fine-tune Llama-3-8B on medical Q&A to build a specialized assistant without paying for proprietary model access.

Heard on the show

“Llama, Gemma, scored the same rigged answers.”

Mentioned in 30 episodes

1. 207
   An AI Graded Its Own Math Test 94 Percent — It Actually Scored 20
2. 183
   Why You Can't Fine-Tune Foresight Into an AI Agent
3. 182
   How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
4. 181
   How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
5. 152
   Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
6. 148
   Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
7. 119
   Beating Reinforcement Learning Without Ever Touching the Model's Weights
8. 118
   Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
9. 108
   The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
10. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model
11. 087
    When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review
12. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
13. 074
    How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
14. 073
    When Three LLMs Talk to Each Other, Their Ideas Quietly Stop Moving
15. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
16. 070
    When Models Know the Answer But Say the Wrong Thing Anyway
17. 069
    When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
18. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
19. 055
    Why LLM Judges Flip Their Verdicts When You Change the Question Format
20. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
21. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
22. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
23. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure
24. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
25. 019
    When the Best Reward Model Trains the Worst Policy: Inside EvoLM
26. 018
    Language Models Compute the Rational Move, Then Override It
27. 015
    The Audit Number Isn't What You Think: Sycophancy and the Case Against Single-Prompt Bias Tests
28. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
29. 004
    The Sycophancy Circuit That Survives Alignment Training
30. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related terms