Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
GPT-5.1 Was Retired on March 11 — Here's What Broke in Your LLM App
Jamie Cole
Jamie Cole
Jamie Cole
Follow
Mar 13
GPT-5.1 Was Retired on March 11 — Here's What Broke in Your LLM App
#
ai
#
llm
#
openai
#
devops
1
reaction
Comments
Add Comment
4 min read
How LLMs Are Transforming Code Review in 2026
Amartya Jha
Amartya Jha
Amartya Jha
Follow
Mar 12
How LLMs Are Transforming Code Review in 2026
#
ai
#
llm
#
codereview
#
programming
Comments
Add Comment
2 min read
Agent-first CLIs are about reducing turns, not JSON
Keyboards Down
Keyboards Down
Keyboards Down
Follow
Mar 12
Agent-first CLIs are about reducing turns, not JSON
#
ai
#
agents
#
llm
#
codingwithai
Comments
Add Comment
4 min read
How Much VRAM Do You Actually Need to Run LLMs Locally?
Max Vyaznikov
Max Vyaznikov
Max Vyaznikov
Follow
Mar 12
How Much VRAM Do You Actually Need to Run LLMs Locally?
#
llm
Comments
Add Comment
3 min read
CodeSpeak: When English Isn't Precise Enough for AI
AttractivePenguin
AttractivePenguin
AttractivePenguin
Follow
Mar 16
CodeSpeak: When English Isn't Precise Enough for AI
#
ai
#
llm
#
kotlin
#
devtools
1
reaction
Comments
Add Comment
5 min read
I Tested 50 AI App Prompts for Injection Attacks. 90% Scored CRITICAL.
Andrei
Andrei
Andrei
Follow
Mar 16
I Tested 50 AI App Prompts for Injection Attacks. 90% Scored CRITICAL.
#
ai
#
security
#
llm
#
webdev
2
reactions
Comments
Add Comment
6 min read
2026年版!AIエージェント開発に必須のオープンソースGitHubリポジトリ10選
youichi11
youichi11
youichi11
Follow
Mar 12
2026年版!AIエージェント開発に必須のオープンソースGitHubリポジトリ10選
#
opensource
#
llm
#
aiアーキテクチャ
#
自律型ai
4
reactions
Comments
Add Comment
2 min read
I asked my AI agent to audit himself. He scored 62/100.
gary-botlington
gary-botlington
gary-botlington
Follow
Mar 15
I asked my AI agent to audit himself. He scored 62/100.
#
ai
#
llm
#
productivity
#
agents
1
reaction
Comments
1
comment
4 min read
Concurrent LLM Serving: Benchmarking vLLM vs SGLang vs Ollama
zkaria gamal
zkaria gamal
zkaria gamal
Follow
Mar 16
Concurrent LLM Serving: Benchmarking vLLM vs SGLang vs Ollama
#
llm
#
ai
#
cloudnative
2
reactions
Comments
Add Comment
2 min read
10 Best vLLM Alternatives for LLM Inference in Production (2026)
Jaipal Singh
Jaipal Singh
Jaipal Singh
Follow
Mar 12
10 Best vLLM Alternatives for LLM Inference in Production (2026)
#
ai
#
llm
#
devops
#
enterprise
1
reaction
Comments
Add Comment
22 min read
Stop Blaming Your LLM: Fix RAG Retrieval Quality With Better Chunking in .NET
Argha Sarkar
Argha Sarkar
Argha Sarkar
Follow
Mar 12
Stop Blaming Your LLM: Fix RAG Retrieval Quality With Better Chunking in .NET
#
dotnet
#
ai
#
rag
#
llm
1
reaction
Comments
Add Comment
7 min read
How I Think About Reliability in LLM Applications
Jamie Gray
Jamie Gray
Jamie Gray
Follow
Mar 12
How I Think About Reliability in LLM Applications
#
ai
#
llm
#
softwareengineering
#
backend
3
reactions
Comments
1
comment
6 min read
Title: Why we built a P2P inference network instead of another AI API wrapper
AntSeed
AntSeed
AntSeed
Follow
Mar 12
Title: Why we built a P2P inference network instead of another AI API wrapper
#
ai
#
llm
#
opensource
#
blockchain
Comments
Add Comment
2 min read
Why Is NullClaw So Small? A Deep Dive into the 678KB AI Coder
Wanda
Wanda
Wanda
Follow
Mar 12
Why Is NullClaw So Small? A Deep Dive into the 678KB AI Coder
#
ai
#
llm
#
opensource
#
tooling
5
reactions
Comments
Add Comment
4 min read
When the AI's memory explodes: context overflow and compaction failures in production
Julio Molina Soler
Julio Molina Soler
Julio Molina Soler
Follow
Mar 12
When the AI's memory explodes: context overflow and compaction failures in production
#
ai
#
devops
#
llm
#
infrastructure
Comments
Add Comment
3 min read
👋
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