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
Sub-Agent Architectures: Patterns, Trade-offs, and a Kotlin Implementation
Zoricic
Zoricic
Zoricic
Follow
Mar 22
Sub-Agent Architectures: Patterns, Trade-offs, and a Kotlin Implementation
#
agents
#
architecture
#
kotlin
#
llm
Comments
Add Comment
11 min read
The Anatomy of an AI Agent: Memory, Tools, Planning, and Execution Explained
Omer Farooq
Omer Farooq
Omer Farooq
Follow
Apr 2
The Anatomy of an AI Agent: Memory, Tools, Planning, and Execution Explained
#
ai
#
agents
#
llm
#
beginners
3
 reactions
Comments
Add Comment
6 min read
Why Faster First Tokens Matter More Than Total Response Time
Amartya Jha
Amartya Jha
Amartya Jha
Follow
Feb 27
Why Faster First Tokens Matter More Than Total Response Time
#
ai
#
llm
#
performance
#
programming
Comments
Add Comment
10 min read
We Spent a Week Evaluating a Context Compression Tool, Then Killed It
AgentAutopsy Team
AgentAutopsy Team
AgentAutopsy Team
Follow
Mar 22
We Spent a Week Evaluating a Context Compression Tool, Then Killed It
#
ai
#
llm
#
agents
#
devops
Comments
1
 comment
6 min read
Designing a Tool Architecture for AI Agents — Base Tools, Toolkits, and Dynamic Routing
Kim Namhyun
Kim Namhyun
Kim Namhyun
Follow
Feb 27
Designing a Tool Architecture for AI Agents — Base Tools, Toolkits, and Dynamic Routing
#
agents
#
ai
#
architecture
#
llm
1
 reaction
Comments
Add Comment
3 min read
Why AI Needs an External Cognitive Layer Beyond Memory
Oleksander
Oleksander
Oleksander
Follow
Apr 2
Why AI Needs an External Cognitive Layer Beyond Memory
#
ai
#
softwareengineering
#
architecture
#
llm
1
 reaction
Comments
Add Comment
3 min read
Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared
LemonData Dev
LemonData Dev
LemonData Dev
Follow
Feb 27
Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared
#
ai
#
programming
#
llm
#
tutorial
Comments
Add Comment
5 min read
LLM Agents Need a Nervous System, Not Just a Brain
GnomeMan4201
GnomeMan4201
GnomeMan4201
Follow
Apr 1
LLM Agents Need a Nervous System, Not Just a Brain
#
ai
#
llm
#
cybersecurity
#
redteam
3
 reactions
Comments
Add Comment
3 min read
I Built a Skill Reviewer. Then I Ran It on Itself.
Shinsuke KAGAWA
Shinsuke KAGAWA
Shinsuke KAGAWA
Follow
Apr 2
I Built a Skill Reviewer. Then I Ran It on Itself.
#
ai
#
llm
#
promptengineering
#
softwareengineering
5
 reactions
Comments
Add Comment
5 min read
We Scanned 12 Popular MCP Servers. Here's What We Found.
Pico
Pico
Pico
Follow
Apr 2
We Scanned 12 Popular MCP Servers. Here's What We Found.
#
security
#
mcp
#
ai
#
llm
1
 reaction
Comments
Add Comment
5 min read
How ChatGPT Actually Predicts Words (Explained Simply)
Rajkiran
Rajkiran
Rajkiran
Follow
Mar 4
How ChatGPT Actually Predicts Words (Explained Simply)
#
ai
#
beginners
#
chatgpt
#
llm
2
 reactions
Comments
Add Comment
2 min read
I Eliminated Layout Jitter From LLM Streaming — Here's How
JAI
JAI
JAI
Follow
Mar 30
I Eliminated Layout Jitter From LLM Streaming — Here's How
#
showdev
#
llm
#
performance
#
webdev
16
 reactions
Comments
Add Comment
4 min read
I Tried Duplicating Layers in Qwen 3.5 to Reduce Hallucinations — Here's What Actually Happened
Dhruv Sharma
Dhruv Sharma
Dhruv Sharma
Follow
Mar 22
I Tried Duplicating Layers in Qwen 3.5 to Reduce Hallucinations — Here's What Actually Happened
#
ai
#
machinelearning
#
llm
#
research
1
 reaction
Comments
Add Comment
5 min read
The OpenClaw ecosystem is exploding. I mapped the key players actually gaining traction.
Sébastien Conejo
Sébastien Conejo
Sébastien Conejo
Follow
Feb 27
The OpenClaw ecosystem is exploding. I mapped the key players actually gaining traction.
#
openclaw
#
agents
#
openai
#
llm
6
 reactions
Comments
1
 comment
1 min read
Why LLM Rate Limits and Throughput Matter More Than Benchmarks
Amartya Jha
Amartya Jha
Amartya Jha
Follow
Feb 27
Why LLM Rate Limits and Throughput Matter More Than Benchmarks
#
ai
#
llm
#
devops
#
programming
Comments
Add Comment
8 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