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
The Agentic Loop Explained: Step Through the Plan, Build, Judge and Repeat Loop Behind AI Coding Agents
DevOps Daily
DevOps Daily
DevOps Daily
Follow
Nov 16
The Agentic Loop Explained: Step Through the Plan, Build, Judge and Repeat Loop Behind AI Coding Agents
#
ai
#
agents
#
llm
#
programming
13
reactions
Comments
2
comments
6 min read
Moderation
LLMs are compressors. So I chatted with gzip
Edoardo Dusi
Edoardo Dusi
Edoardo Dusi
Follow
for
AWS
Nov 16
LLMs are compressors. So I chatted with gzip
#
llm
#
compression
#
aws
#
serverless
12
reactions
Comments
Add Comment
12 min read
Moderation
Your MCP Servers Eat 24,000 Tokens Before You Type
Aditya Negandhi
Aditya Negandhi
Aditya Negandhi
Follow
Nov 16
Your MCP Servers Eat 24,000 Tokens Before You Type
#
mcp
#
llm
#
cost
#
ai
Comments
1
comment
6 min read
Moderation
I let an LLM fill my AI tools directory. 11 months later, 41% of its picks were dead.
Vlad Gerasimchuk
Vlad Gerasimchuk
Vlad Gerasimchuk
Follow
Nov 16
I let an LLM fill my AI tools directory. 11 months later, 41% of its picks were dead.
#
ai
#
llm
#
webdev
#
seo
Comments
Add Comment
6 min read
Moderation
The Rigor Ratchet: adversarial field notes from testing a frontier preview model on myself
KL3FT3Z
KL3FT3Z
KL3FT3Z
Follow
Nov 16
The Rigor Ratchet: adversarial field notes from testing a frontier preview model on myself
#
ai
#
webdev
#
security
#
llm
1
reaction
Comments
2
comments
5 min read
Moderation
Speculative Decoding Acceptance Rate: Why 70% Caps You Near 2x
jidonglab
jidonglab
jidonglab
Follow
Nov 16
Speculative Decoding Acceptance Rate: Why 70% Caps You Near 2x
#
llm
#
machinelearning
#
performance
#
ai
Comments
1
comment
7 min read
Moderation
How to get up to 2.3 faster GLM and DeepSeek inference by switching providers
Sergey Inozemtsev
Sergey Inozemtsev
Sergey Inozemtsev
Follow
Nov 16
How to get up to 2.3 faster GLM and DeepSeek inference by switching providers
#
llm
#
performance
#
deepseek
#
ai
Comments
Add Comment
4 min read
Moderation
One Question to a RAG Chatbot Leaked Another Customer's Secret Price
Bug Bounty & Beyond
Bug Bounty & Beyond
Bug Bounty & Beyond
Follow
Nov 16
One Question to a RAG Chatbot Leaked Another Customer's Secret Price
#
security
#
ai
#
llm
#
tutorial
Comments
Add Comment
2 min read
Moderation
Um modelo de 1.7B consegue igualar um LLM 4,7x maior? Destilando o Qwen3-8B com QLoRA em avaliações reais em PT-BR
Matheus Soares
Matheus Soares
Matheus Soares
Follow
Nov 16
Um modelo de 1.7B consegue igualar um LLM 4,7x maior? Destilando o Qwen3-8B com QLoRA em avaliações reais em PT-BR
#
machinelearning
#
llm
#
python
#
nlp
1
reaction
Comments
Add Comment
9 min read
Moderation
How I run an AI software factory
Sunny Golovine
Sunny Golovine
Sunny Golovine
Follow
Nov 16
How I run an AI software factory
#
ai
#
llm
Comments
Add Comment
2 min read
Moderation
Using AI for Anonymity
Brian Tarbox
Brian Tarbox
Brian Tarbox
Follow
for
AWS Heroes
Nov 15
Using AI for Anonymity
#
ai
#
llm
#
writing
9
reactions
Picked as gem
Picked as gem by you
Comments
Add Comment
6 min read
Moderation
Prompt injection is a permissions problem
Sayam Jain
Sayam Jain
Sayam Jain
Follow
Nov 16
Prompt injection is a permissions problem
#
ai
#
llm
#
security
Comments
Add Comment
7 min read
Moderation
Qwen4-Max: Alibaba's Biggest Model Yet Is Cheap, and Closed
Mohammad Hassan Amer
Mohammad Hassan Amer
Mohammad Hassan Amer
Follow
Nov 16
Qwen4-Max: Alibaba's Biggest Model Yet Is Cheap, and Closed
#
ai
#
llm
#
programming
#
opensource
Comments
1
comment
3 min read
Moderation
How to Tell Whether the Model Behind Your API Got Worse
Mayur Agnani
Mayur Agnani
Mayur Agnani
Follow
Nov 16
How to Tell Whether the Model Behind Your API Got Worse
#
ai
#
observability
#
machinelearning
#
llm
Comments
1
comment
3 min read
Moderation
What I Cut First When Reviewing a Multi-Subagent AI Architecture
Taiki Mishima
Taiki Mishima
Taiki Mishima
Follow
Nov 16
What I Cut First When Reviewing a Multi-Subagent AI Architecture
#
ai
#
agents
#
architecture
#
llm
1
reaction
Comments
Add Comment
9 min read
Moderation
👋
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