AIQB
TutorialsOrdinary

I tested whether a 4B model could replace a 12B one in a tool-using agent. My first test was wrong.

Source: DEV Community·

Summary

Two pre-registered runs on local models, a reader's correction between them, and the one place the...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-0ed9b878342809e62f298f15
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Don't Trust the Mint Button: A Read-Only Guard That Verifies BSC Mints On-Chain Before Anyone Signs
This article is my entry for the zkVerify Agent Games Creator Track. #AgentGames Every "free mint"...
Source: DEV Community
TutorialsOrdinary
Three of the first 18 GitHub repos I tested were malware
In September I was building a small tool called Legwork. The idea: when your AI assistant needs a...
Source: DEV Community
TutorialsOrdinary
My AI Agent Works for Me Every Day. Here's How I Make It Prove Everything.
An entry for the zkVerify Agent Games — Creator Track. #AgentGames I don't run demos. My AI agent —...
Source: DEV Community
TutorialsOrdinary
A prompt-injected model cannot skip your approval step
A human-in-the-loop design usually has the same shape: the model proposes an action, the graph stops...
Source: DEV Community
TutorialsOrdinary
Claude Code Hooks: Deterministic Guardrails for AI Coding Agents — Field Notes
Headline: A rule in CLAUDE.md is a request the model usually follows; a Claude Code hook is a...
Source: DEV Community · Claude
TutorialsOrdinary
Your Agent Is Still a while (true) Loop. Here's the Event Log That Replaced Mine.
An agent crashes mid-run and there's no answer to "what state was it in." Not because the debugging...
Source: DEV Community
TutorialsOrdinary
Running a dense 33B agent model on one 24 GB GPU: the offload trap and the empty reply
Nanbeige4.3-33B ran at about 42 tokens/s on one RTX 4090 with llama.cpp. Why offload fails for dense models, and the empty-reply bug to watch.
Source: DEV Community · Llama
TutorialsOrdinary
Jira said Done. It wasn't, and the bug showed up later. So I made Jira check first.
Picture this. The ticket moved to Done on Friday. The pull request was merged, CI was green, everyone...
Source: DEV Community
TutorialsOrdinary
Your 1M-Context Model Is Wasted on Sloppy Instruc
I know the feeling. You watched the Opus 5.5 launch notes drop on September 22, saw "1M context,...
Source: DEV Community
TutorialsOrdinary
Every new model has a 1M-token context window. Do you still need retrieval?
Look at the model releases from October alone: DeepSeek V4.1 Flash, MiniMax M3.1 Flash, Kimi K3.1...
Source: DEV Community · DeepSeek / Kimi