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
Agentic Workflows vs. Prompt Engineering: Which One Saves More Time?
Ravi Kumar Vishwakarma
Ravi Kumar Vishwakarma
Ravi Kumar Vishwakarma
Follow
Feb 3
Agentic Workflows vs. Prompt Engineering: Which One Saves More Time?
#
agents
#
ai
#
llm
#
productivity
1
 reaction
Comments
Add Comment
16 min read
Benchmarks Are Breaking: Why Many ‘Top Scores’ Don’t Mean Production-Ready.
Lamhot Siagian
Lamhot Siagian
Lamhot Siagian
Follow
Feb 22
Benchmarks Are Breaking: Why Many ‘Top Scores’ Don’t Mean Production-Ready.
#
llm
#
ai
1
 reaction
Comments
Add Comment
7 min read
If you don't red-team your LLM app, your users will
Lamhot Siagian
Lamhot Siagian
Lamhot Siagian
Follow
Feb 22
If you don't red-team your LLM app, your users will
#
ai
#
llm
#
evaluation
#
security
1
 reaction
Comments
Add Comment
7 min read
Accuracy Is Expensive: How to Evaluate ‘Quality per $’ for Agents and RAG
Lamhot Siagian
Lamhot Siagian
Lamhot Siagian
Follow
Feb 22
Accuracy Is Expensive: How to Evaluate ‘Quality per $’ for Agents and RAG
#
ai
#
llm
#
rag
1
 reaction
Comments
Add Comment
6 min read
Superpowers: The Technology to "Persuade" AI Agents—Why Psychological Principles Change Code Quality
tumf
tumf
tumf
Follow
Jan 30
Superpowers: The Technology to "Persuade" AI Agents—Why Psychological Principles Change Code Quality
#
ai
#
llm
#
casual
Comments
Add Comment
5 min read
claude-switcher: The Concept of Piping Prompts into Unix
tumf
tumf
tumf
Follow
Jan 30
claude-switcher: The Concept of Piping Prompts into Unix
#
ai
#
llm
#
shellscript
Comments
Add Comment
5 min read
Claude Prompt Leaks via Tool Abuse: Expert Blueprint to Secure AI Tooling in 2026
Delafosse Olivier
Delafosse Olivier
Delafosse Olivier
Follow
Feb 10
Claude Prompt Leaks via Tool Abuse: Expert Blueprint to Secure AI Tooling in 2026
#
ai
#
machinelearning
#
llm
#
programming
Comments
Add Comment
6 min read
Why AI Output Fails Before Generation Ever Begins
Leigh k Valentine
Leigh k Valentine
Leigh k Valentine
Follow
Jan 29
Why AI Output Fails Before Generation Ever Begins
#
ai
#
architecture
#
llm
#
systemdesign
5
 reactions
Comments
1
 comment
8 min read
Mastering Mistral API Costs: A Deep Dive into Pricing Models and Optimization Strategies
Life is Good
Life is Good
Life is Good
Follow
Jan 29
Mastering Mistral API Costs: A Deep Dive into Pricing Models and Optimization Strategies
#
llm
#
mistral
#
api
#
costoptimization
Comments
Add Comment
6 min read
Developing with Claude Code? You should be using Checkmate!
André Bremer
André Bremer
André Bremer
Follow
Jan 29
Developing with Claude Code? You should be using Checkmate!
#
programming
#
ai
#
agents
#
llm
Comments
Add Comment
3 min read
Why Your MCP Server Sucks (And How to Fix It)
Aman Kumar
Aman Kumar
Aman Kumar
Follow
Jan 28
Why Your MCP Server Sucks (And How to Fix It)
#
mcp
#
ai
#
llm
#
cursor
2
 reactions
Comments
Add Comment
5 min read
Agentic Mesh in the Wild
choutos
choutos
choutos
Follow
Feb 20
Agentic Mesh in the Wild
#
ai
#
agents
#
llm
#
architecture
3
 reactions
Comments
Add Comment
5 min read
Building with A2UI: Extending the Expressiveness of AI Agent Interfaces
Médéric Hurier (Fmind)
Médéric Hurier (Fmind)
Médéric Hurier (Fmind)
Follow
Feb 6
Building with A2UI: Extending the Expressiveness of AI Agent Interfaces
#
architecture
#
llm
#
frontend
#
artificialintelligen
Comments
Add Comment
7 min read
Silent Degradation in LLM Systems: Detecting When Your AI Quietly Gets Worse
Delafosse Olivier
Delafosse Olivier
Delafosse Olivier
Follow
Feb 10
Silent Degradation in LLM Systems: Detecting When Your AI Quietly Gets Worse
#
ai
#
machinelearning
#
llm
#
programming
2
 reactions
Comments
1
 comment
5 min read
Don’t Trust Your Agents. Trust Your Boundary: a runtime authorization layer for LLM tool calls.
NAOL ZEWUDU
NAOL ZEWUDU
NAOL ZEWUDU
Follow
Jan 28
Don’t Trust Your Agents. Trust Your Boundary: a runtime authorization layer for LLM tool calls.
#
agents
#
ai
#
llm
#
security
Comments
Add Comment
6 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