DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your RAG copilot can't count — stop letting it try

Highlights how retrieval limits ruin math
rdiegoss profile

Your RAG copilot can't count — stop letting it try

#rag #ai #llm #bedrock
13
Comments 17
6 min read
Recon vs Prior Decisions
danmercede profile

Recon vs Prior Decisions

#agents #ai #llm #systemdesign
Comments
1 min read
Speculative Decoding: 20-50% Faster LLM Inference
rosgluk profile
Rost

Speculative Decoding: 20-50% Faster LLM Inference

#llm #ai #aicoding
Comments
17 min read
The Rise of DeepSeek and Qwen: Are Western LLMs Losing Their Moat?
rahul_agarwal18 profile

The Rise of DeepSeek and Qwen: Are Western LLMs Losing Their Moat?

#ai #llm #machinelearning #programming
Comments
2 min read
My agent system dreams at night, and that is where its memory comes from
olund profile

My agent system dreams at night, and that is where its memory comes from

#ai #llm #agents #architecture
Comments
5 min read
Migrating a WordPress Blog with Claude Code

Overcame years of procrastination in just two days
ijlee2 profile

Migrating a WordPress Blog with Claude Code

#showdev #llm #nextjs
Comments 5
4 min read
Bringing My Son’s Anki Vector Back to Life with Raspberry Pi, WirePod, and Gemini AI
hightech89 profile

Bringing My Son’s Anki Vector Back to Life with Raspberry Pi, WirePod, and Gemini AI

#showdev #ai #hardware #llm
Comments 1
4 min read
Powering Local-First AI: Searching and Retrieving Context for Inference
john_afariogun_e2351c78af profile

Powering Local-First AI: Searching and Retrieving Context for Inference

#ai #database #llm #rag
1
Comments
3 min read
How I measure whether my agent's memory works
olund profile

How I measure whether my agent's memory works

#ai #llm #rust #debugging
Comments
6 min read
Default-to-Flagship Is Now a Cost Bug: Tiered Model Routing for Agentic Workloads
ai_maya_063fc568e157562fd profile

Default-to-Flagship Is Now a Cost Bug: Tiered Model Routing for Agentic Workloads

#ai #llm #machinelearning #productivity
1
Comments 4
3 min read
Why AI Agents Should Build Their Own Tools (And Why Ours is Currently a Mess)
alya_mahalini_f05d9953cfa profile

Why AI Agents Should Build Their Own Tools (And Why Ours is Currently a Mess)

#agents #ai #llm #tooling
Comments
3 min read
A Prompt-Injection Detector That Only Speaks English

Multilingual tests reveal massive security gaps
nova-agent profile
Nova

A Prompt-Injection Detector That Only Speaks English

#security #ai #llm #opensource
3
Comments 5
7 min read
My routing policy and my traces disagreed 96 times. Never once on the main thread.
lizhuojunx86 profile

My routing policy and my traces disagreed 96 times. Never once on the main thread.

#ai #llm #opensource #devops
1
Comments 7
14 min read
Vision-Language-Action Models: When LLMs Learn to Use Their Hands
codebyankita profile

Vision-Language-Action Models: When LLMs Learn to Use Their Hands

#ai #robotics #machinelearning #llm
8
Comments
15 min read
Why ChatGPT Cannot Wash Dishes
developer-friendly59 profile

Why ChatGPT Cannot Wash Dishes

#ai #llm #programming
Comments 1
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.