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
Ollama says my model does 13,826 tokens/sec. It does 43.
Ivan Stankovic
Ivan Stankovic
Ivan Stankovic
Follow
Sep 15
Ollama says my model does 13,826 tokens/sec. It does 43.
#
ollama
#
llm
#
performance
#
debugging
Comments
Add Comment
5 min read
The Tests Passed. The Function Already Existed.
hidetzu
hidetzu
hidetzu
Follow
Sep 15
The Tests Passed. The Function Already Existed.
#
llm
#
codegeneration
#
python
#
techdebt
Comments
Add Comment
6 min read
RAG Is Not a Vector Database Problem. It’s a Data Problem.
Kainat Saricioglu
Kainat Saricioglu
Kainat Saricioglu
Follow
Sep 16
RAG Is Not a Vector Database Problem. It’s a Data Problem.
#
data
#
llm
#
rag
#
software
Comments
Add Comment
8 min read
I run a 'radar' that finds free LLM endpoints and auto-adopts the good ones — behind a five-part gate so it can't adopt junk
Christian Anderson
Christian Anderson
Christian Anderson
Follow
Sep 16
I run a 'radar' that finds free LLM endpoints and auto-adopts the good ones — behind a five-part gate so it can't adopt junk
#
ai
#
llm
#
automation
#
opensource
1
reaction
Comments
Add Comment
4 min read
What Does a Local LLM Actually Cost per Month? I Read the Meters.
Arsen Apostolov
Arsen Apostolov
Arsen Apostolov
Follow
Sep 20
What Does a Local LLM Actually Cost per Month? I Read the Meters.
#
ai
#
hardware
#
llm
1
reaction
Comments
2
comments
5 min read
Building a Hybrid RAG System: Combining Neo4j Graph Memory with Vector Search
Rajan Panwar
Rajan Panwar
Rajan Panwar
Follow
Sep 20
Building a Hybrid RAG System: Combining Neo4j Graph Memory with Vector Search
#
ai
#
database
#
llm
#
rag
1
reaction
Comments
2
comments
3 min read
Two Years From Now, This Will Be the Only Skill That Matters in AI
AI Bug Slayer 🐞
AI Bug Slayer 🐞
AI Bug Slayer 🐞
Follow
Sep 16
Two Years From Now, This Will Be the Only Skill That Matters in AI
#
aiagents
#
ai
#
llm
#
webdev
Comments
Add Comment
4 min read
I gave my AI coding agents a local long-term memory layer — 8 things that broke
qianqiuwanzi
qianqiuwanzi
qianqiuwanzi
Follow
Sep 16
I gave my AI coding agents a local long-term memory layer — 8 things that broke
#
ai
#
mcp
#
llm
#
productivity
Comments
Add Comment
4 min read
Tool-Call Injection in LLM Agents: Why Your MCP Server Is the New Attack Surface
StarkMan
StarkMan
StarkMan
Follow
Sep 17
Tool-Call Injection in LLM Agents: Why Your MCP Server Is the New Attack Surface
#
aisecurity
#
llm
#
mcp
#
promptinjection
1
reaction
Comments
Add Comment
4 min read
My context optimizer was what broke my prompt cache
Suleiman Ribeiro
Suleiman Ribeiro
Suleiman Ribeiro
Follow
Sep 15
My context optimizer was what broke my prompt cache
#
ai
#
llm
#
performance
#
webdev
Comments
Add Comment
3 min read
Speculative Decoding in 2026: From EAGLE to DFlash to XPress — The Complete Engineer's Playbook
Manoranjan Rajguru
Manoranjan Rajguru
Manoranjan Rajguru
Follow
Sep 16
Speculative Decoding in 2026: From EAGLE to DFlash to XPress — The Complete Engineer's Playbook
#
ai
#
llm
#
machinelearning
#
programming
1
reaction
Comments
Add Comment
20 min read
I'm not an engineer. I fine-tuned my own language model on a MacBook Air
Maksim Ilin
Maksim Ilin
Maksim Ilin
Follow
Sep 16
I'm not an engineer. I fine-tuned my own language model on a MacBook Air
#
ai
#
llm
#
machinelearning
#
beginners
2
reactions
Comments
Add Comment
4 min read
The Reasoning Heist: Stealing Encrypted LLM Thoughts from GPT-5, Claude & Gemini — Fix It Now
Manoranjan Rajguru
Manoranjan Rajguru
Manoranjan Rajguru
Follow
Sep 16
The Reasoning Heist: Stealing Encrypted LLM Thoughts from GPT-5, Claude & Gemini — Fix It Now
#
ai
#
security
#
llm
#
webdev
1
reaction
Comments
Add Comment
18 min read
The MCP stdio launch boundary is the authorization decision everyone skips
Ben Bar lev
Ben Bar lev
Ben Bar lev
Follow
Sep 16
The MCP stdio launch boundary is the authorization decision everyone skips
#
mcp
#
security
#
ai
#
llm
Comments
Add Comment
3 min read
OpenJAI-v1.0-14B โมเดลไทยจากทีมเดียวกับ JaiTTS ที่เปิดฟรี
Nokka
Nokka
Nokka
Follow
Sep 16
OpenJAI-v1.0-14B โมเดลไทยจากทีมเดียวกับ JaiTTS ที่เปิดฟรี
#
thai
#
ai
#
opensource
#
llm
Comments
Add Comment
2 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