AIQB
TutorialsOrdinary

SFT vs. RL: What Changes Inside the Model?

Source: DEV Community·

Summary

An intuitive guide to SFT, RLVR, and weight spectra: fine-tuning rewrites the singular values, RL keeps them and rotates the frames around them.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-ed77f7ac6d7466e508781029
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Swarms sound like the future, but most teams can’t debug them — here’s when peer-to-peer actually pays off — Swarms / P2P
I spent a week watching a swarm of six agents burn through $400 in tokens, hand off a billing...
Source: DEV Community
TutorialsOrdinary
4 Months of vox-bench in Production — What 14,000 Benchmark Runs Taught Us About Voice AI Latency
In June, we open-sourced vox-bench, the latency benchmarking tool we built after a TTS spike caused...
Source: DEV Community
TutorialsOrdinary
GraphSentinel- Agentic fraud investigation
GraphSentinel: Building an Agentic Fraud Investigation System on TigerGraph Fraud...
Source: DEV Community
TutorialsOrdinary
How to work with AI like a Senior Developer
A practical workflow for turning generated code into changes you can understand, verify, and...
Source: DEV Community
TutorialsOrdinary
Harness Engineering 101: How Coding Agents Actually Work
What an agent harness is, and why the same model solved 43 tasks in one harness and 72 in another. With Claude Code, Codex and six more coding agents compared.
Source: DEV Community · Claude
TutorialsOrdinary
From 48M Records to Top 8 Finalists: How We Built an End-to-End Urban Flow AI
We have some exciting news to share! 🎉 Our team, DataMinds, competed in the prestigious SLIIT...
Source: DEV Community
TutorialsOrdinary
I gave my AI agent one harmless permission. It became a backdoor for everyone.
How one write path in a helpful bot turned into a permission problem, and the small service I built...
Source: DEV Community
TutorialsOrdinary
Quicksilver: The Company That Operates Itself
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
Source: DEV Community
TutorialsOrdinary
The 22 patterns of AI code slop, and how to delete them
AI agents ship code that reads like quality and isn't. Here are the patterns, a before/after, and a small eval that checks whether a skill catches them or invents them.
Source: DEV Community
TutorialsOrdinary
This video is about how this video was made
This video (the script, the voice timings, the source code, the storyboard, the briefs the subagents...
Source: DEV Community