Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Prompt‑Powered User Personas: From Messy Logs to Living Profiles
Dechun Wang
Dechun Wang
Dechun Wang
Follow
Dec 10 '25
Prompt‑Powered User Personas: From Messy Logs to Living Profiles
#
ai
#
promptengineering
#
llm
Comments
1
 comment
14 min read
Why your AI assistant lies to you (and how to fix it)
Sandeep Salwan
Sandeep Salwan
Sandeep Salwan
Follow
Dec 11 '25
Why your AI assistant lies to you (and how to fix it)
#
ai
#
rag
#
llm
#
machinelearning
Comments
Add Comment
4 min read
Prompt Length vs. Context Window: The Real Limits Behind LLM Performance
Dechun Wang
Dechun Wang
Dechun Wang
Follow
Dec 10 '25
Prompt Length vs. Context Window: The Real Limits Behind LLM Performance
#
ai
#
llm
#
promptengineering
#
machinelearning
1
 reaction
Comments
1
 comment
4 min read
Context-Optimized APIs: Designing MCP Servers for LLMs
Rich Jeffries
Rich Jeffries
Rich Jeffries
Follow
Nov 29 '25
Context-Optimized APIs: Designing MCP Servers for LLMs
#
ai
#
mcp
#
llm
#
api
1
 reaction
Comments
Add Comment
5 min read
LangGraph Streaming 101: 5 Modes to Build Responsive AI Applications
Seenivasa Ramadurai
Seenivasa Ramadurai
Seenivasa Ramadurai
Follow
Dec 10 '25
LangGraph Streaming 101: 5 Modes to Build Responsive AI Applications
#
agents
#
llm
#
ai
#
tutorial
1
 reaction
Comments
4
 comments
6 min read
I Built a Distributed AI Search Engine That Lets Websites 'Talk' Directly to LLMs (No Indexing Required)
Oleg Yaruchyk
Oleg Yaruchyk
Oleg Yaruchyk
Follow
Dec 11 '25
I Built a Distributed AI Search Engine That Lets Websites 'Talk' Directly to LLMs (No Indexing Required)
#
showdev
#
ai
#
llm
#
python
5
 reactions
Comments
Add Comment
8 min read
The Hell of AI Agent Development
Masaaki Hirano
Masaaki Hirano
Masaaki Hirano
Follow
Dec 10 '25
The Hell of AI Agent Development
#
discuss
#
ai
#
llm
#
blogging
5
 reactions
Comments
2
 comments
8 min read
Taming Opus 4.5's Efficiency: Using TodoWrite to Keep Claude Code on Track
Shinsuke KAGAWA
Shinsuke KAGAWA
Shinsuke KAGAWA
Follow
Dec 11 '25
Taming Opus 4.5's Efficiency: Using TodoWrite to Keep Claude Code on Track
#
ai
#
productivity
#
programming
#
llm
Comments
Add Comment
2 min read
Local LLM Hosting: Complete 2025 Guide - Ollama, vLLM, LocalAI, Jan, LM Studio & More
Rost
Rost
Rost
Follow
Nov 29 '25
Local LLM Hosting: Complete 2025 Guide - Ollama, vLLM, LocalAI, Jan, LM Studio & More
#
llm
#
ai
#
ollama
#
privacy
1
 reaction
Comments
Add Comment
19 min read
A Financial MCP server with multi-provider orchestration (Open Source)
Kiarash
Kiarash
Kiarash
Follow
Nov 29 '25
A Financial MCP server with multi-provider orchestration (Open Source)
#
ai
#
python
#
llm
#
mcp
Comments
Add Comment
1 min read
Supercharge Your Fish Shell: Stop Googling, Start Commanding with AI
GitHubOpenSource
GitHubOpenSource
GitHubOpenSource
Follow
Dec 10 '25
Supercharge Your Fish Shell: Stop Googling, Start Commanding with AI
#
fish
#
ai
#
command
#
llm
Comments
Add Comment
3 min read
Demystifying Agentic Test Automation for QA Teams
John Vester
John Vester
John Vester
Follow
Dec 10 '25
Demystifying Agentic Test Automation for QA Teams
#
ai
#
llm
#
testing
#
programming
2
 reactions
Comments
Add Comment
5 min read
“I've failed 17 consecutive times with the exact same error”
Derek Cheng
Derek Cheng
Derek Cheng
Follow
for
Tonkotsu AI Inc.
Dec 9 '25
“I've failed 17 consecutive times with the exact same error”
#
llm
#
agents
#
ai
#
devtool
1
 reaction
Comments
Add Comment
5 min read
We built an LLM gateway 50x faster than LiteLLM (and it's open source)
Kuldeep Paul
Kuldeep Paul
Kuldeep Paul
Follow
Dec 9 '25
We built an LLM gateway 50x faster than LiteLLM (and it's open source)
#
opensource
#
ai
#
go
#
llm
6
 reactions
Comments
Add Comment
3 min read
CLaRa: Fixing RAG’s Broken Retrieval–Generation Pipeline With Shared-Space Learning
Mudassir Khan
Mudassir Khan
Mudassir Khan
Follow
Dec 9 '25
CLaRa: Fixing RAG’s Broken Retrieval–Generation Pipeline With Shared-Space Learning
#
rag
#
llm
#
architecture
#
machinelearning
3
 reactions
Comments
Add Comment
3 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account