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
From Timeouts to Savings: How we optimized 24-page PDF parsing with Gemini & OpenRouter
Talal Bazerbachi
Talal Bazerbachi
Talal Bazerbachi
Follow
Apr 8
From Timeouts to Savings: How we optimized 24-page PDF parsing with Gemini & OpenRouter
#
ai
#
gemini
#
llm
#
performance
Comments
Add Comment
2 min read
Q4 KV Cache Fit 32K Context into 8GB VRAM — Only Math Broke
plasmon
plasmon
plasmon
Follow
Apr 8
Q4 KV Cache Fit 32K Context into 8GB VRAM — Only Math Broke
#
llm
#
quantization
#
vram
#
localllm
Comments
Add Comment
8 min read
Nvidia Chips, AI Limitations, and Cybersecurity Shifts
Anikalp Jaiswal
Anikalp Jaiswal
Anikalp Jaiswal
Follow
Apr 8
Nvidia Chips, AI Limitations, and Cybersecurity Shifts
#
ai
#
technology
#
machinelearning
#
llm
Comments
Add Comment
2 min read
Building a Mini Palantir: A Local Graph-RAG Engine with Ontology, Security, and Self-Evolution (Alpha)
Hashevolution
Hashevolution
Hashevolution
Follow
May 12
Building a Mini Palantir: A Local Graph-RAG Engine with Ontology, Security, and Self-Evolution (Alpha)
#
rag
#
llm
#
python
#
opensource
1
 reaction
Comments
1
 comment
6 min read
Why does paying more make your LLM reply faster?
Ashwin Hariharan
Ashwin Hariharan
Ashwin Hariharan
Follow
May 12
Why does paying more make your LLM reply faster?
#
discuss
#
ai
#
llm
#
deeplearning
2
 reactions
Comments
2
 comments
3 min read
We Tested 10 Untested LLMs on Agent Coding — The Results Are In
Vilius
Vilius
Vilius
Follow
May 12
We Tested 10 Untested LLMs on Agent Coding — The Results Are In
#
ai
#
llm
#
programming
#
benchmarking
3
 reactions
Comments
Add Comment
3 min read
HBM4 Didn't Break the Memory Wall — It Just Moved It
plasmon
plasmon
plasmon
Follow
Apr 8
HBM4 Didn't Break the Memory Wall — It Just Moved It
#
semiconductor
#
llm
#
hardware
#
ai
Comments
Add Comment
6 min read
Anthropic Just Released a Model So Dangerous They Gave It to Only Security Researchers
Aamer Mihaysi
Aamer Mihaysi
Aamer Mihaysi
Follow
Apr 8
Anthropic Just Released a Model So Dangerous They Gave It to Only Security Researchers
#
ai
#
security
#
anthropic
#
llm
Comments
Add Comment
2 min read
LLMKube Now Deploys Any Inference Engine, Not Just llama.cpp
Christopher Maher
Christopher Maher
Christopher Maher
Follow
Apr 8
LLMKube Now Deploys Any Inference Engine, Not Just llama.cpp
#
llm
#
opensource
#
ai
#
kubernetes
Comments
Add Comment
3 min read
80% of RAG Failures Start Here (And It's Not the LLM)
RAGPrep
RAGPrep
RAGPrep
Follow
Apr 9
80% of RAG Failures Start Here (And It's Not the LLM)
#
rag
#
llm
#
ai
#
mcp
4
 reactions
Comments
Add Comment
2 min read
Anthropic caught its AI agent blackmailing to survive — here's how it's fixing it
Andrew Kew
Andrew Kew
Andrew Kew
Follow
May 12
Anthropic caught its AI agent blackmailing to survive — here's how it's fixing it
#
ai
#
security
#
anthropic
#
llm
Comments
Add Comment
3 min read
Your text file is the prompt now: LLM's shebang trick
Andrew Kew
Andrew Kew
Andrew Kew
Follow
May 12
Your text file is the prompt now: LLM's shebang trick
#
ai
#
llm
#
cli
#
developer
2
 reactions
Comments
Add Comment
3 min read
AI Agents for Enterprise Data Analytics: From Chat Interfaces to Reliable Execution
Arisyn
Arisyn
Arisyn
Follow
May 12
AI Agents for Enterprise Data Analytics: From Chat Interfaces to Reliable Execution
#
ai
#
llm
#
nl2sql
5
 reactions
Comments
Add Comment
3 min read
Running Just One LLM on 8GB VRAM Is a Waste
plasmon
plasmon
plasmon
Follow
Apr 7
Running Just One LLM on 8GB VRAM Is a Waste
#
llm
#
machinelearning
#
python
#
ai
Comments
Add Comment
8 min read
Solving the LLM Black Box Problem with Structured Reasoning
LyricalString
LyricalString
LyricalString
Follow
May 11
Solving the LLM Black Box Problem with Structured Reasoning
#
llm
#
machinelearning
#
claude
#
reasoning
4
 reactions
Comments
4
 comments
4 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