eBook
The Craft of Post-Training : A Practical Guide for AI Engineers and Developers
| Title: | The Craft of Post-Training : A Practical Guide for AI Engineers and Developers |
|---|---|
| Description: | Capable by default. Reliable by design.A pre-trained model has read most of the internet—and can be trusted with almost none of it. Post-training is the work that changes that: where you take a raw, general model and shape it into something that behaves, follows instructions, refuses what it shouldn't do, and handles the specific job you need. It's the human hand on the machine, and the part almost no one explains.Chris von Csefalvay has spent his career building production ML systems in industry, from clinical language to legal text. In The Craft of Post-Training, he shows you the decisions behind every technique: when to fine-tune and when not to, why a model quietly gets worse, and which method fits the constraint you're actually under. The math is here, because knowing why a technique works is what lets you debug it when it breaks.You'll know how to:Choose among the main post-training methods, from SFT and RLHF to DPO, KTO, and GRPO, well enough to fix failures instead of guessingAdapt a model to your domain without catastrophic forgetting—the tendency of a network to abruptly overwrite what it already knew when you train it on something newRun larger models with the memory you have by using new quantizationTrain agentic systems to act reliably under adversarial pressureMeasure what matters in your deployment, beyond standard benchmarksWhen you've used LLMs long enough, you start to wonder what was done to make them behave. The secret is in the post-training that shaped them. The Craft of Post-Training shows you how that's done. |
| Authors: | Chris Von Csefalvay |
| Resource Type: | eBook. |
| Categories: | COMPUTERS / Artificial Intelligence / Natural Language Processing, COMPUTERS / Languages / Python, COMPUTERS / Data Science / Machine Learning |
| Database: | eBook Index |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: edsebk DbLabel: eBook Index An: 4491006 RelevancyScore: 987 AccessLevel: 6 PubType: eBook PubTypeId: ebook PreciseRelevancyScore: 987.310668945313 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: The Craft of Post-Training : A Practical Guide for AI Engineers and Developers – Name: Abstract Label: Description Group: Ab Data: Capable by default. Reliable by design.A pre-trained model has read most of the internet—and can be trusted with almost none of it. Post-training is the work that changes that: where you take a raw, general model and shape it into something that behaves, follows instructions, refuses what it shouldn't do, and handles the specific job you need. It's the human hand on the machine, and the part almost no one explains.Chris von Csefalvay has spent his career building production ML systems in industry, from clinical language to legal text. In The Craft of Post-Training, he shows you the decisions behind every technique: when to fine-tune and when not to, why a model quietly gets worse, and which method fits the constraint you're actually under. The math is here, because knowing why a technique works is what lets you debug it when it breaks.You'll know how to:Choose among the main post-training methods, from SFT and RLHF to DPO, KTO, and GRPO, well enough to fix failures instead of guessingAdapt a model to your domain without catastrophic forgetting—the tendency of a network to abruptly overwrite what it already knew when you train it on something newRun larger models with the memory you have by using new quantizationTrain agentic systems to act reliably under adversarial pressureMeasure what matters in your deployment, beyond standard benchmarksWhen you've used LLMs long enough, you start to wonder what was done to make them behave. The secret is in the post-training that shaped them. The Craft of Post-Training shows you how that's done. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chris+Von+Csefalvay%22">Chris Von Csefalvay</searchLink> – Name: TypePub Label: Resource Type Group: TypPub Data: eBook. – Name: SubjectBISAC Label: Categories Group: Su Data: <searchLink fieldCode="ZK" term="%22COMPUTERS+%2F+Artificial+Intelligence+%2F+Natural+Language+Processing%22">COMPUTERS / Artificial Intelligence / Natural Language Processing</searchLink><br /><searchLink fieldCode="ZK" term="%22COMPUTERS+%2F+Languages+%2F+Python%22">COMPUTERS / Languages / Python</searchLink><br /><searchLink fieldCode="ZK" term="%22COMPUTERS+%2F+Data+Science+%2F+Machine+Learning%22">COMPUTERS / Data Science / Machine Learning</searchLink> |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=4491006 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English Titles: – TitleFull: The Craft of Post-Training : A Practical Guide for AI Engineers and Developers Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chris Von Csefalvay – PersonEntity: Name: NameFull: Chris Von Csefalvay IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2026 Identifiers: – Type: isbn-print Value: 9781718505209 – Type: isbn-electronic Value: 9781718505216 Titles: – TitleFull: The Craft of Post-Training : A Practical Guide for AI Engineers and Developers Type: main |
| ResultId | 1 |