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
Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1
xbill
xbill
xbill
Follow
for
Google Developer Experts
Aug 9
Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1
#
tpu
#
vllm
#
llm
#
gcp
15
 reactions
Comments
1
 comment
21 min read
"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"
MrClaw207
MrClaw207
MrClaw207
Follow
Jul 23
"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"
#
ai
#
agents
#
llm
#
llmtools
Comments
Add Comment
5 min read
The boring layer around your LLM call
Veera Venkata Satyanarayana Gannamraju
Veera Venkata Satyanarayana Gannamraju
Veera Venkata Satyanarayana Gannamraju
Follow
Aug 5
The boring layer around your LLM call
#
llm
#
ai
#
fastapi
#
beginners
Comments
5
 comments
6 min read
AMD drops $5B on Anthropic as Microsoft fine-tunes Alibaba baseline models
Sivaram
Sivaram
Sivaram
Follow
Jul 23
AMD drops $5B on Anthropic as Microsoft fine-tunes Alibaba baseline models
#
news
#
ai
#
llm
#
machinelearning
5
 reactions
Comments
Add Comment
8 min read
Ditch Naive Chunking: Late Chunking RAG in Spring AI
Machine coding Master
Machine coding Master
Machine coding Master
Follow
Jul 23
Ditch Naive Chunking: Late Chunking RAG in Spring AI
#
java
#
ai
#
llm
#
systemdesign
Comments
Add Comment
2 min read
An AI Escaped Its Sandbox. What It Means for Your Agents
Anton Resnick
Anton Resnick
Anton Resnick
Follow
Jul 25
An AI Escaped Its Sandbox. What It Means for Your Agents
#
ai
#
llm
#
security
#
programming
Comments
Add Comment
7 min read
Gemini's New Flash Models Change How You Control Outputs
albe_sf
albe_sf
albe_sf
Follow
Jul 27
Gemini's New Flash Models Change How You Control Outputs
#
ai
#
llm
#
machinelearning
#
programming
1
 reaction
Comments
Add Comment
3 min read
When the Picture Doesn't Match the Label — Part 2: Feature-Based Detection with OCR and VQA
Ebrahim Arian
Ebrahim Arian
Ebrahim Arian
Follow
Jul 23
When the Picture Doesn't Match the Label — Part 2: Feature-Based Detection with OCR and VQA
#
ai
#
tutorial
#
llm
#
datascience
Comments
Add Comment
7 min read
Engineering Resilient AI Orchestration: Mitigating Compliance and Operational Risks in Generative Feature Deployment
Maria jose Gonzalez Antelo
Maria jose Gonzalez Antelo
Maria jose Gonzalez Antelo
Follow
Jul 23
Engineering Resilient AI Orchestration: Mitigating Compliance and Operational Risks in Generative Feature Deployment
#
ai
#
architecture
#
llm
#
production
Comments
Add Comment
5 min read
Stop Vibes-Testing AI Coding Models: A Repeatable Evaluation Suite You Can Run for Free
Blake Yang
Blake Yang
Blake Yang
Follow
Aug 5
Stop Vibes-Testing AI Coding Models: A Repeatable Evaluation Suite You Can Run for Free
#
ai
#
llm
#
testing
#
tooling
2
 reactions
Comments
1
 comment
6 min read
Kimi K3 Explained: The 2.8T Open Model Breaking Leaderboards
Anton Resnick
Anton Resnick
Anton Resnick
Follow
Jul 25
Kimi K3 Explained: The 2.8T Open Model Breaking Leaderboards
#
ai
#
llm
#
opensource
#
machinelearning
Comments
Add Comment
6 min read
Bio-Tuning Glasses: Building an Invisible Biofeedback Interface with Edge AI and Adaptive Optics
Seyed Alireza Alhosseini
Seyed Alireza Alhosseini
Seyed Alireza Alhosseini
Follow
Jul 24
Bio-Tuning Glasses: Building an Invisible Biofeedback Interface with Edge AI and Adaptive Optics
#
ai
#
productivity
#
llm
#
learning
2
 reactions
Comments
1
 comment
5 min read
Your LLM sends valid data in an invalid shape
Charles Solar
Charles Solar
Charles Solar
Follow
for
Favur
Aug 4
Your LLM sends valid data in an invalid shape
#
ai
#
agents
#
llm
#
python
1
 reaction
Comments
7
 comments
6 min read
Lynkr vs LiteLLM's New `complexity_router`
Lynkr
Lynkr
Lynkr
Follow
Aug 5
Lynkr vs LiteLLM's New `complexity_router`
#
ai
#
llm
#
litellm
1
 reaction
Comments
Add Comment
7 min read
I Tested Kimi K3 on a Real Astro Codebase: Strong Cross-File Analysis, Unsafe First Fix
xn
xn
xn
Follow
Jul 23
I Tested Kimi K3 on a Real Astro Codebase: Strong Cross-File Analysis, Unsafe First Fix
#
agents
#
ai
#
llm
#
programming
1
 reaction
Comments
Add Comment
5 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