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
I Tried to Sneak Four Bad Agents Past My Own Certification Gate. All Four Got Blocked.
Debashish Ghosal
Debashish Ghosal
Debashish Ghosal
Follow
Oct 1
I Tried to Sneak Four Bad Agents Past My Own Certification Gate. All Four Got Blocked.
#
ai
#
llm
#
testing
#
agents
16
reactions
Comments
3
comments
5 min read
Xiaomi AI training, live: what the MiMo 2.6 RL dashboard shows
Nikoloz Turazashvili (@axrisi)
Nikoloz Turazashvili (@axrisi)
Nikoloz Turazashvili (@axrisi)
Follow
Oct 1
Xiaomi AI training, live: what the MiMo 2.6 RL dashboard shows
#
news
#
ai
#
llm
#
machinelearning
1
reaction
Comments
1
comment
9 min read
Scaling Intelligence: Running LLMs Across a Seven-Board ESP32-S3 Cluster
Lightning Developer
Lightning Developer
Lightning Developer
Follow
Oct 1
Scaling Intelligence: Running LLMs Across a Seven-Board ESP32-S3 Cluster
#
esp32
#
edgeai
#
llm
#
embedded
6
reactions
Comments
Add Comment
4 min read
Cutting 70% of RAG context tokens and keeping the answers identical (measured)
gj0xv
gj0xv
gj0xv
Follow
Oct 1
Cutting 70% of RAG context tokens and keeping the answers identical (measured)
#
ai
#
llm
#
rag
#
python
Comments
Add Comment
3 min read
You Can Parallelize Agents. You Cannot Parallelize the Engineer.
The Skills Team
The Skills Team
The Skills Team
Follow
Oct 1
You Can Parallelize Agents. You Cannot Parallelize the Engineer.
#
agents
#
ai
#
llm
#
productivity
1
reaction
Comments
Add Comment
4 min read
A 404 is the easy half. Scoring a package that actually exists is where we got it wrong.
jj1423
jj1423
jj1423
Follow
Oct 1
A 404 is the easy half. Scoring a package that actually exists is where we got it wrong.
#
agents
#
cybersecurity
#
llm
#
security
2
reactions
Comments
4
comments
5 min read
Voice-to-SQL: hablarle a tu base de datos con un LLM (y por qué la seguridad es lo difícil)
Adrian
Adrian
Adrian
Follow
Oct 1
Voice-to-SQL: hablarle a tu base de datos con un LLM (y por qué la seguridad es lo difícil)
#
nlp
#
texttosql
#
llm
#
webspeechapi
Comments
Add Comment
3 min read
MCP Is Becoming the New Attack Surface: Securing the Next Generation of AI Agents
Manikandan Mariappan
Manikandan Mariappan
Manikandan Mariappan
Follow
Oct 1
MCP Is Becoming the New Attack Surface: Securing the Next Generation of AI Agents
#
ai
#
mcp
#
llm
#
models
1
reaction
Comments
Add Comment
9 min read
Kimi K3, DeepSeek and GLM free from NVIDIA: I tested the claim and here is the catch
Kirill Lukyanov
Kirill Lukyanov
Kirill Lukyanov
Follow
Oct 1
Kimi K3, DeepSeek and GLM free from NVIDIA: I tested the claim and here is the catch
#
ai
#
llm
#
opensource
#
api
6
reactions
Comments
Add Comment
3 min read
How to estimate your LLM inference bill before you ship (with Python)
Andrea Susic
Andrea Susic
Andrea Susic
Follow
Oct 1
How to estimate your LLM inference bill before you ship (with Python)
#
ai
#
tutorial
#
python
#
llm
Comments
Add Comment
8 min read
When Chat Templates Go Wrong
pielouNW
pielouNW
pielouNW
Follow
Oct 1
When Chat Templates Go Wrong
#
llm
#
opensource
#
ai
#
llamacpp
Comments
Add Comment
7 min read
Open WebUI: Admin Configuration Options in a Nutshell
Sebastian
Sebastian
Sebastian
Follow
Oct 1
Open WebUI: Admin Configuration Options in a Nutshell
#
ai
#
agents
#
llm
#
openwebui
Comments
Add Comment
12 min read
I rented an A100 to test one vLLM flag
Throttle
Throttle
Throttle
Follow
Oct 1
I rented an A100 to test one vLLM flag
#
infrastructure
#
llm
#
performance
Comments
Add Comment
2 min read
How I Built an Enterprise Sales Agent with a Lower-Cost LLM—and Server-Side Guardrails
Abdul Rasith
Abdul Rasith
Abdul Rasith
Follow
Oct 1
How I Built an Enterprise Sales Agent with a Lower-Cost LLM—and Server-Side Guardrails
#
agents
#
ai
#
llm
#
productivity
1
reaction
Comments
Add Comment
2 min read
How I cut my LLM bill by 54.9%: a local router that costs $0 per decision
gj0xv
gj0xv
gj0xv
Follow
Oct 1
How I cut my LLM bill by 54.9%: a local router that costs $0 per decision
#
ai
#
llm
#
python
#
opensource
Comments
Add Comment
3 min read
👋
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