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
The Agentic Gap: Claude Oneshots, Gemma Fails
Rob
Rob
Rob
Follow
May 8
The Agentic Gap: Claude Oneshots, Gemma Fails
#
ai
#
llm
#
benchmark
#
homelab
Comments
Add Comment
9 min read
Model Showdown Round 2: Adding Gemma, Kimi, and 579 GB of Stubborn Optimism
Rob
Rob
Rob
Follow
May 8
Model Showdown Round 2: Adding Gemma, Kimi, and 579 GB of Stubborn Optimism
#
ai
#
llm
#
benchmark
#
homelab
Comments
Add Comment
11 min read
Slaying the Gemma Beast: How We Fixed Local AI and Shipped Search
Rob
Rob
Rob
Follow
May 8
Slaying the Gemma Beast: How We Fixed Local AI and Shipped Search
#
ai
#
llm
#
benchmark
#
homelab
Comments
Add Comment
13 min read
Putting the GPU to Work: Running Local LLMs on a Home Lab
Rob
Rob
Rob
Follow
May 8
Putting the GPU to Work: Running Local LLMs on a Home Lab
#
ai
#
homelab
#
llm
Comments
Add Comment
10 min read
Paper opinion: Execution Lineage vs Agent Loops (arXiv 2605.06365)
Kuro
Kuro
Kuro
Follow
May 8
Paper opinion: Execution Lineage vs Agent Loops (arXiv 2605.06365)
#
agents
#
llm
#
ai
#
research
Comments
Add Comment
4 min read
LLM-Based AI Agent Architecture: A New Kind of Personal Computer on Your Device
code plato
code plato
code plato
Follow
May 8
LLM-Based AI Agent Architecture: A New Kind of Personal Computer on Your Device
#
ai
#
llm
#
agents
#
architecture
Comments
Add Comment
4 min read
Six Reliability Primitives for LLM Agents
Mukunda Rao Katta
Mukunda Rao Katta
Mukunda Rao Katta
Follow
May 8
Six Reliability Primitives for LLM Agents
#
ai
#
llm
#
mcp
#
opensource
1
reaction
Comments
2
comments
3 min read
We Do Not Teach Thinking to AI
Dechive
Dechive
Dechive
Follow
May 9
We Do Not Teach Thinking to AI
#
discuss
#
ai
#
llm
#
productivity
1
reaction
Comments
Add Comment
2 min read
The problem wasn't that the AI wrote bad code — weak specs caused unstable implementations
Nirsa
Nirsa
Nirsa
Follow
May 8
The problem wasn't that the AI wrote bad code — weak specs caused unstable implementations
#
ai
#
architecture
#
llm
#
softwareengineering
Comments
Add Comment
2 min read
Why RAG is Like Playing Space Invaders. The Higher the Level the More Difficult it Becomes to Win.
Russel Hawkins
Russel Hawkins
Russel Hawkins
Follow
May 8
Why RAG is Like Playing Space Invaders. The Higher the Level the More Difficult it Becomes to Win.
#
discuss
#
ai
#
llm
#
rag
Comments
Add Comment
15 min read
GPT-5.5 Just Raised the Bar for Everyone — And It's Not About Benchmarks
Chetan Sehgal
Chetan Sehgal
Chetan Sehgal
Follow
May 8
GPT-5.5 Just Raised the Bar for Everyone — And It's Not About Benchmarks
#
ai
#
llm
#
agents
#
openai
Comments
Add Comment
3 min read
What is Model Context Protocol (MCP)? A Developer’s Guide
Serhii Kalyna
Serhii Kalyna
Serhii Kalyna
Follow
May 8
What is Model Context Protocol (MCP)? A Developer’s Guide
#
ai
#
llm
#
mcp
#
tutorial
1
reaction
Comments
Add Comment
3 min read
AI 週報 — 2026-05-08 MS-OpenAI 合作鬆動,AI 競賽轉向控制面
Yang Goufang
Yang Goufang
Yang Goufang
Follow
May 8
AI 週報 — 2026-05-08 MS-OpenAI 合作鬆動,AI 競賽轉向控制面
#
ai
#
machinelearning
#
tech
#
llm
Comments
Add Comment
5 min read
AI Weekly — 2026-05-08 | MS-OpenAI loosens, and the race moves to control
Yang Goufang
Yang Goufang
Yang Goufang
Follow
May 8
AI Weekly — 2026-05-08 | MS-OpenAI loosens, and the race moves to control
#
ai
#
machinelearning
#
tech
#
llm
Comments
Add Comment
9 min read
Quando a IA mente e te pede CALMA: um papo reto sobre alucinações
Marcelo Cabral Ghilardi
Marcelo Cabral Ghilardi
Marcelo Cabral Ghilardi
Follow
May 8
Quando a IA mente e te pede CALMA: um papo reto sobre alucinações
#
ia
#
llm
#
alucinacao
#
comportamentoia
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