Jev glossary
Evaluation & TrainingThe Bitter Lesson
The Bitterest Lesson
TypeSafe's essay extending Sutton's lesson: doing the right task beats data, which beats compute, which beats algorithms.
- Category
- Evaluation & Training
- Also known as
- The Bitter Lesson
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 1
- Docs
- typesafe.ai
- Added
- 2026-09-24
Definition
The post orders the leverage in ML as doing the right task > data > compute > algorithms, using InstructGPT as its example: GPT-2-sized models over 100x smaller than GPT-3 beat it once trained on the right task.
It argues that scaling pre-training would have needed roughly GPT-7 level to beat that baseline and GPT-9 to beat InstructGPT on GPT-3, and that picking the right task often means leaving ML to study users, products, and organizations.
Tagstrainingresearch
Related terms
Definitions that connect to this one.
RLCDTypeSafe's post-training method: reinforcement learning that optimizes for calibrated decisions and probabilities instead of generated text.Evaluation & TrainingWorkflow evalsTypeSafe's published evaluations of four automation workflows, comparing Jev and frontier LLMs as structured workflows versus single prompts.Evaluation & TrainingTypeSafe AIThe company behind Jev and the System One API, including the official SDKs, cookbooks, console, and published workflow evals.Core Concepts
From the Jev directory
Directory entries that go deeper on this term.
A TypeSafe blog essay arguing that in ML the order that matters is doing the right task, then data, then compute, then algorithms, using the InstructGPT result as its example.
Jev Guides & ArticlesArticle#official#article#models
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.