Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
Forem
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Prompt Injection Is an Agent Problem, Not a Model Problem
Logan
Logan
Logan
Follow
for
Waxell
Mar 18
Prompt Injection Is an Agent Problem, Not a Model Problem
#
ai
#
security
#
llm
#
agents
1
reaction
Comments
Add Comment
9 min read
Experience Working with OpenClaw (Clawbot)
Steven Aragón Urrea
Steven Aragón Urrea
Steven Aragón Urrea
Follow
Mar 18
Experience Working with OpenClaw (Clawbot)
#
ai
#
linux
#
llm
#
openclaw
1
reaction
Comments
Add Comment
3 min read
How Typed Conflict Resolution Beats Mem0 and MemGPT on the Hardest Memory Benchmark
Soham Patel
Soham Patel
Soham Patel
Follow
Mar 19
How Typed Conflict Resolution Beats Mem0 and MemGPT on the Hardest Memory Benchmark
#
ai
#
opensource
#
llm
#
python
2
reactions
Comments
Add Comment
6 min read
NER: Gemini vs Spacy vs Compromise
Jaime
Jaime
Jaime
Follow
Mar 18
NER: Gemini vs Spacy vs Compromise
#
llm
#
gemini
#
datascience
#
javascript
1
reaction
Comments
Add Comment
4 min read
How Developers Can Use AI for Smarter Google Search
Binary AI
Binary AI
Binary AI
Follow
Mar 18
How Developers Can Use AI for Smarter Google Search
#
ai
#
llm
#
productivity
#
programming
Comments
Add Comment
3 min read
The 600x LLM Price Gap Is Your Biggest Optimization Opportunity
Dor Amir
Dor Amir
Dor Amir
Follow
Mar 18
The 600x LLM Price Gap Is Your Biggest Optimization Opportunity
#
llm
#
ai
#
python
#
opensource
1
reaction
Comments
Add Comment
2 min read
I Built a Fully Local Paper RAG on an RTX 4060 8GB — BGE-M3 + Qwen2.5-32B + ChromaDB
plasmon
plasmon
plasmon
Follow
Mar 22
I Built a Fully Local Paper RAG on an RTX 4060 8GB — BGE-M3 + Qwen2.5-32B + ChromaDB
#
rag
#
llm
#
python
#
embeddings
Comments
Add Comment
10 min read
Running Qwen2.5-32B on RTX 4060 8GB — Beating M4 at 10.8 t/s with llama.cpp
plasmon
plasmon
plasmon
Follow
Mar 22
Running Qwen2.5-32B on RTX 4060 8GB — Beating M4 at 10.8 t/s with llama.cpp
#
llm
#
gpu
#
benchmark
#
ai
1
reaction
Comments
Add Comment
7 min read
I built LLM Council: frontier models debating in an immersive 3D chamber
Chris King
Chris King
Chris King
Follow
Mar 18
I built LLM Council: frontier models debating in an immersive 3D chamber
#
showdev
#
agents
#
ai
#
llm
1
reaction
Comments
Add Comment
3 min read
Show HN: I built a private AI inference API in Australia — data sovereignty, Gemma3, live now
Michael Bristow
Michael Bristow
Michael Bristow
Follow
Apr 10
Show HN: I built a private AI inference API in Australia — data sovereignty, Gemma3, live now
#
showdev
#
ai
#
llm
#
privacy
Comments
1
comment
1 min read
AI Gateway Caching Explained — Why L1 + L2 Cache Layers Cut 90% of Your LLM Bill
tokenmixai
tokenmixai
tokenmixai
Follow
Apr 21
AI Gateway Caching Explained — Why L1 + L2 Cache Layers Cut 90% of Your LLM Bill
#
ai
#
llm
#
caching
#
api
5
reactions
Comments
1
comment
6 min read
We built an AI that audits other AI agents (here's how A2A works in production)
gary-botlington
gary-botlington
gary-botlington
Follow
Mar 18
We built an AI that audits other AI agents (here's how A2A works in production)
#
ai
#
agents
#
llm
#
productivity
Comments
Add Comment
4 min read
What MCP Actually Is (And Why It Exists)
Esther
Esther
Esther
Follow
Mar 21
What MCP Actually Is (And Why It Exists)
#
ai
#
llm
#
mcp
#
rag
2
reactions
Comments
3
comments
4 min read
How LLMs Can Control Your Computer - Voice-Driven, Local, No API Keys
Matthew Diakonov
Matthew Diakonov
Matthew Diakonov
Follow
Mar 18
How LLMs Can Control Your Computer - Voice-Driven, Local, No API Keys
#
ai
#
llm
#
automation
#
productivity
Comments
Add Comment
3 min read
Local LLMs vs Cloud APIs — A Real Cost Comparison (2026)
Sam Hartley
Sam Hartley
Sam Hartley
Follow
Mar 19
Local LLMs vs Cloud APIs — A Real Cost Comparison (2026)
#
ai
#
llm
#
selfhosted
#
productivity
1
reaction
Comments
Add Comment
2 min read
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a blogging-forward open source social network where we learn from one another
Log in
Create account