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
MCP Tool Poisoning: The AI Supply Chain Attack Nobody Is Talking About
Aevris AI
Aevris AI
Aevris AI
Follow
May 2
MCP Tool Poisoning: The AI Supply Chain Attack Nobody Is Talking About
#
ai
#
security
#
mcp
#
llm
Comments
2
 comments
4 min read
The 7-Layer Memory Architecture Behind Modern AI Agents
Mahmoud Zalt
Mahmoud Zalt
Mahmoud Zalt
Follow
May 23
The 7-Layer Memory Architecture Behind Modern AI Agents
#
ai
#
agents
#
llm
#
memory
1
 reaction
Comments
Add Comment
7 min read
BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090
#
ai
#
llm
#
inference
#
opensource
Comments
Add Comment
3 min read
Anna's Archive llms.txt: a routing guide for LLM crawlers
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
Anna's Archive llms.txt: a routing guide for LLM crawlers
#
news
#
ai
#
llm
#
dataset
Comments
Add Comment
3 min read
Semantic caching thresholds and why they matter
Drishti Shah
Drishti Shah
Drishti Shah
Follow
for
Portkey
Apr 22
Semantic caching thresholds and why they matter
#
ai
#
llm
#
nlp
#
performance
Comments
Add Comment
12 min read
Five habits that separate the operator from the vibe-coder
Aman Bhandari
Aman Bhandari
Aman Bhandari
Follow
Apr 19
Five habits that separate the operator from the vibe-coder
#
ai
#
claudecode
#
agents
#
llm
Comments
Add Comment
6 min read
Gate Zero: stop unfalsifiable prompts before they canonicalize as specs
Aman Bhandari
Aman Bhandari
Aman Bhandari
Follow
Apr 19
Gate Zero: stop unfalsifiable prompts before they canonicalize as specs
#
ai
#
claudecode
#
promptengineering
#
llm
Comments
Add Comment
5 min read
Eval-driven development for a local-LLM agent: how I shipped Lore 0.2.0 with confidence
Erez Shahaf
Erez Shahaf
Erez Shahaf
Follow
Apr 18
Eval-driven development for a local-LLM agent: how I shipped Lore 0.2.0 with confidence
#
agents
#
llm
#
opensource
#
testing
1
 reaction
Comments
Add Comment
6 min read
Your Claude Code rules are a liability you'll never audit
Aman Bhandari
Aman Bhandari
Aman Bhandari
Follow
Apr 19
Your Claude Code rules are a liability you'll never audit
#
claudecode
#
ai
#
promptengineering
#
llm
Comments
Add Comment
6 min read
Qwen 3.6 Ollama Release, Consumer GPU Benchmarks, GGUF Quantization Fixes
soy
soy
soy
Follow
Apr 18
Qwen 3.6 Ollama Release, Consumer GPU Benchmarks, GGUF Quantization Fixes
#
ai
#
llm
#
selfhosted
Comments
Add Comment
4 min read
Gemini 3.5 Flash beat 3.1 Pro on coding and agents
Thousand Miles AI
Thousand Miles AI
Thousand Miles AI
Follow
May 23
Gemini 3.5 Flash beat 3.1 Pro on coding and agents
#
news
#
ai
#
llm
#
gemini
Comments
Add Comment
3 min read
How to Run STRIDE-AI on Your AI Stack in One Pass
ToxSec
ToxSec
ToxSec
Follow
May 22
How to Run STRIDE-AI on Your AI Stack in One Pass
#
security
#
ai
#
llm
#
threatmodeling
Comments
2
 comments
4 min read
luckrig: a concept for tasting LLM rigs, not just models
gen
gen
gen
Follow
May 22
luckrig: a concept for tasting LLM rigs, not just models
#
showdev
#
llm
#
opensource
#
machinelearning
Comments
1
 comment
2 min read
Your MCP Server Is Probably Overprivileged - Here's a Scanner For It
David McHale
David McHale
David McHale
Follow
May 22
Your MCP Server Is Probably Overprivileged - Here's a Scanner For It
#
ai
#
security
#
llm
#
javascript
2
 reactions
Comments
Add Comment
2 min read
The Speculative Decoding Pattern
Ken W Alger
Ken W Alger
Ken W Alger
Follow
May 22
The Speculative Decoding Pattern
#
ai
#
llm
#
machinelearning
#
performance
4
 reactions
Comments
2
 comments
3 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