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
Colibri: Running a 744B AI Model on Your Laptop
jamilxt
jamilxt
jamilxt
Follow
Jul 17
Colibri: Running a 744B AI Model on Your Laptop
#
ai
#
llm
#
machinelearning
#
performance
1
 reaction
Comments
Add Comment
5 min read
The eye corrects the ear: fixing my LLM's video hallucinations with OCR and a VAD gate
Leo Huang
Leo Huang
Leo Huang
Follow
Jul 17
The eye corrects the ear: fixing my LLM's video hallucinations with OCR and a VAD gate
#
ai
#
whisper
#
llm
#
opensource
Comments
4
 comments
2 min read
Anthropic Was Right About One Thing: Broad Safety Decisions Are Dangerous
Gen.Y.Sakai
Gen.Y.Sakai
Gen.Y.Sakai
Follow
Jun 13
Anthropic Was Right About One Thing: Broad Safety Decisions Are Dangerous
#
ai
#
llm
#
programming
#
claude
Comments
Add Comment
42 min read
The Source-of-Truth Problem Every Enterprise AI Team Faces
Karan Padhiyar
Karan Padhiyar
Karan Padhiyar
Follow
Jun 18
The Source-of-Truth Problem Every Enterprise AI Team Faces
#
ai
#
llm
#
rag
#
brainpackai
1
 reaction
Comments
Add Comment
3 min read
Setting Up a Local AI Coding Agent with Ollama and Aider (part 3)
eleonorarocchi
eleonorarocchi
eleonorarocchi
Follow
Jul 17
Setting Up a Local AI Coding Agent with Ollama and Aider (part 3)
#
llm
#
ai
Comments
Add Comment
5 min read
My AI System Logged 35,669 LLM Calls. It Still Couldn’t Tell Me What They Cost.
Dariusz Newecki
Dariusz Newecki
Dariusz Newecki
Follow
Jun 13
My AI System Logged 35,669 LLM Calls. It Still Couldn’t Tell Me What They Cost.
#
ai
#
llm
#
governance
#
devlog
Comments
Add Comment
7 min read
I almost burned ₹4,000 on Claude API overnight — so I built llm-cost-guard
Advik
Advik
Advik
Follow
Jun 13
I almost burned ₹4,000 on Claude API overnight — so I built llm-cost-guard
#
node
#
typescript
#
llm
#
opensource
Comments
Add Comment
3 min read
Metadata Filtering Before Vector Search: The Recall Win Nobody Measures
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jun 13
Metadata Filtering Before Vector Search: The Recall Win Nobody Measures
#
rag
#
ai
#
llm
#
database
Comments
Add Comment
7 min read
A required field made my AI fabricate statistics
Martin Schenk
Martin Schenk
Martin Schenk
Follow
Jul 17
A required field made my AI fabricate statistics
#
ai
#
llm
#
promptengineering
#
buildinpublic
Comments
2
 comments
5 min read
MCP na prática: Tools, Resources e quando usar cada um
Higor Morais
Higor Morais
Higor Morais
Follow
Jun 17
MCP na prática: Tools, Resources e quando usar cada um
#
ai
#
llm
#
mcp
#
tutorial
1
 reaction
Comments
Add Comment
9 min read
Moonshot AI's Kimi K3 Is Here: A 2.8 Trillion Parameter Open MoE Model That Pushes Long-Context AI Forward
SRAurora Tech
SRAurora Tech
SRAurora Tech
Follow
Jul 17
Moonshot AI's Kimi K3 Is Here: A 2.8 Trillion Parameter Open MoE Model That Pushes Long-Context AI Forward
#
ai
#
genai
#
rag
#
llm
1
 reaction
Comments
Add Comment
3 min read
Top 10 Open Source & Open-Weight AI Models in July 2026: Capabilities, Architecture, and Estimated Training Costs
Sreeraj Sreenivasan
Sreeraj Sreenivasan
Sreeraj Sreenivasan
Follow
Jul 17
Top 10 Open Source & Open-Weight AI Models in July 2026: Capabilities, Architecture, and Estimated Training Costs
#
ai
#
machinelearning
#
llm
#
opensource
Comments
Add Comment
19 min read
Getting an LLM to Actually Follow Your Output Format (Without Fighting It Every Request)
KNALLHART.DEV
KNALLHART.DEV
KNALLHART.DEV
Follow
Jun 26
Getting an LLM to Actually Follow Your Output Format (Without Fighting It Every Request)
#
ai
#
llm
#
javascript
#
webdev
2
 reactions
Comments
2
 comments
3 min read
Self-Hosting Your First LLM for Enterprise: What Nobody Tells You Before You Start
Nolan Vale
Nolan Vale
Nolan Vale
Follow
Jun 17
Self-Hosting Your First LLM for Enterprise: What Nobody Tells You Before You Start
#
ai
#
infrastructure
#
llm
#
tutorial
2
 reactions
Comments
Add Comment
3 min read
Rate limiting, email alerts, health checks, and Grafana — what we shipped to make Ajah production-ready
Vignesh Reddy
Vignesh Reddy
Vignesh Reddy
Follow
Jun 13
Rate limiting, email alerts, health checks, and Grafana — what we shipped to make Ajah production-ready
#
api
#
devops
#
llm
#
monitoring
Comments
Add Comment
2 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