Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
Forem
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Stop Caching the Whole LLM Response. Cache the Embedding.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
Stop Caching the Whole LLM Response. Cache the Embedding.
#
ai
#
rag
#
llm
#
observability
Comments
Add Comment
8 min read
GEO / AI Search Thread
cited
cited
cited
Follow
Apr 27
GEO / AI Search Thread
#
discuss
#
ai
#
llm
#
marketing
Comments
Add Comment
5 min read
Why Apple Is Pivoting Hard Toward On-Device AI in 2026
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
Why Apple Is Pivoting Hard Toward On-Device AI in 2026
#
ai
#
llm
#
architecture
#
agents
Comments
Add Comment
7 min read
Vibe Coding Just Failed Its First Real Audit
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
Vibe Coding Just Failed Its First Real Audit
#
ai
#
programming
#
llm
#
codequality
Comments
Add Comment
8 min read
Hugging Face Pulled Dozens of Backdoored Models. Here's the Pattern.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
Hugging Face Pulled Dozens of Backdoored Models. Here's the Pattern.
#
ai
#
security
#
llm
#
agents
Comments
Add Comment
7 min read
The 100-Line LLM Cache That Pays For Itself in a Week
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
The 100-Line LLM Cache That Pays For Itself in a Week
#
ai
#
llm
#
observability
#
python
Comments
Add Comment
8 min read
Anthropic Skills Is Quietly Killing the Prompt Management Category
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
Anthropic Skills Is Quietly Killing the Prompt Management Category
#
ai
#
llm
#
prompt
#
promptengineering
Comments
Add Comment
7 min read
The Single Unit Test Every LLM Prompt Should Have
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
The Single Unit Test Every LLM Prompt Should Have
#
ai
#
llm
#
prompt
#
tutorial
Comments
Add Comment
7 min read
The 6-Line Postgres Migration That Halved a Team's LLM Bill
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
The 6-Line Postgres Migration That Halved a Team's LLM Bill
#
database
#
postgres
#
llm
#
observability
Comments
Add Comment
7 min read
OpenAI Outage Postmortem: What Status Pages Don't Tell You
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
OpenAI Outage Postmortem: What Status Pages Don't Tell You
#
llm
#
observability
#
devops
#
ai
Comments
Add Comment
7 min read
The 2-Line Defense That Stops 90% of Real-World Prompt Injection
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Apr 26
The 2-Line Defense That Stops 90% of Real-World Prompt Injection
#
ai
#
llm
#
security
#
prompt
Comments
Add Comment
7 min read
I built an MCP server for a knowledge graph. It doesn't call any LLM.
TyKolt
TyKolt
TyKolt
Follow
May 10
I built an MCP server for a knowledge graph. It doesn't call any LLM.
#
mcp
#
ai
#
llm
#
rust
1
 reaction
Comments
2
 comments
2 min read
AI Agent Persona Gone Rogue: 140 Direct Edits and the Foreman Pattern
Steven Gonsalvez
Steven Gonsalvez
Steven Gonsalvez
Follow
Apr 26
AI Agent Persona Gone Rogue: 140 Direct Edits and the Foreman Pattern
#
agents
#
ai
#
claude
#
llm
Comments
Add Comment
3 min read
Why I Stopped Counting Tokens: Building a Zero‑Token Cognition Engine
NILE GREEN
NILE GREEN
NILE GREEN
Follow
Apr 27
Why I Stopped Counting Tokens: Building a Zero‑Token Cognition Engine
#
ai
#
architecture
#
llm
#
api
Comments
Add Comment
1 min read
Prompt Injection in AI Coding Agents: 3 Attack Vectors, 4 Defenses
Sahil Kathpal
Sahil Kathpal
Sahil Kathpal
Follow
Apr 26
Prompt Injection in AI Coding Agents: 3 Attack Vectors, 4 Defenses
#
agents
#
ai
#
llm
#
security
Comments
Add Comment
12 min read
đź‘‹
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