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
How I track per-customer LLM costs in production
John Medina
John Medina
John Medina
Follow
May 15
How I track per-customer LLM costs in production
#
llm
#
opensource
#
ai
#
costtracking
Comments
Add Comment
2 min read
Building Functional Selfhood in AI
dake zhang
dake zhang
dake zhang
Follow
May 16
Building Functional Selfhood in AI
#
agents
#
ai
#
llm
#
opensource
Comments
Add Comment
51 min read
LLM observability tools are blind to the voice layer. Here is what I checked 6 of them for.
Marcus Chen
Marcus Chen
Marcus Chen
Follow
Jun 18
LLM observability tools are blind to the voice layer. Here is what I checked 6 of them for.
#
ai
#
observability
#
llm
#
machinelearning
1
 reaction
Comments
2
 comments
3 min read
Claude Mythos vs Claude Opus 4.6: what the leaked benchmarks mean for developers
Preecha
Preecha
Preecha
Follow
May 16
Claude Mythos vs Claude Opus 4.6: what the leaked benchmarks mean for developers
#
news
#
ai
#
claude
#
llm
Comments
Add Comment
5 min read
Structured Outputs vs Free-Form Summaries: Notes from an AI Regulatory Monitoring Build
andrii oliinyk
andrii oliinyk
andrii oliinyk
Follow
May 15
Structured Outputs vs Free-Form Summaries: Notes from an AI Regulatory Monitoring Build
#
ai
#
llm
#
architecture
Comments
Add Comment
2 min read
Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal
soy
soy
soy
Follow
May 15
Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal
#
ai
#
llm
#
selfhosted
Comments
Add Comment
3 min read
Designing Voice Agents Like Chips: Coverage Closure for Agent FSMs
Peter
Peter
Peter
Follow
May 15
Designing Voice Agents Like Chips: Coverage Closure for Agent FSMs
#
agents
#
ai
#
llm
#
testing
Comments
Add Comment
7 min read
Part 6 — RAG Recall Quality from 60% to 93%: Building a Continuous Evaluation Loop (Not Gut Feeling)
James Lee
James Lee
James Lee
Follow
Jun 18
Part 6 — RAG Recall Quality from 60% to 93%: Building a Continuous Evaluation Loop (Not Gut Feeling)
#
llm
#
performance
#
rag
#
softwareengineering
7
 reactions
Comments
2
 comments
10 min read
Note taking can save you millions of TOKENs. Here is how
Prasenjeet Kumar
Prasenjeet Kumar
Prasenjeet Kumar
Follow
May 16
Note taking can save you millions of TOKENs. Here is how
#
llm
#
ai
#
coding
#
productivity
Comments
Add Comment
1 min read
I loaded 30 days of real LLM traces into a live demo. Here is what they reveal
Adarsh Rao
Adarsh Rao
Adarsh Rao
Follow
May 15
I loaded 30 days of real LLM traces into a live demo. Here is what they reveal
#
ai
#
llm
#
selfhosted
#
observability
Comments
Add Comment
2 min read
Building Scrollbook: What I Learned Building and Scaling an AI Game Master Platform as a Solo Engineer
Dusty Mumphrey
Dusty Mumphrey
Dusty Mumphrey
Follow
May 15
Building Scrollbook: What I Learned Building and Scaling an AI Game Master Platform as a Solo Engineer
#
aiengineering
#
systemdesign
#
gamedev
#
llm
Comments
Add Comment
6 min read
The LLM 429 you didn't plan for: which rate-limit dimension binds first
LLM Cap Planner
LLM Cap Planner
LLM Cap Planner
Follow
May 15
The LLM 429 you didn't plan for: which rate-limit dimension binds first
#
programming
#
ai
#
llm
#
webdev
Comments
Add Comment
3 min read
The LLM rate limit that 429s you first is rarely the one you sized for — so I gave my agent a tool to compute it
SolvoHQ
SolvoHQ
SolvoHQ
Follow
May 15
The LLM rate limit that 429s you first is rarely the one you sized for — so I gave my agent a tool to compute it
#
mcp
#
ai
#
llm
#
programming
Comments
Add Comment
4 min read
Search in the LLM Era: Vector RAG vs Vectorless Search vs LLM-Wiki
Siraj Lakhani
Siraj Lakhani
Siraj Lakhani
Follow
May 16
Search in the LLM Era: Vector RAG vs Vectorless Search vs LLM-Wiki
#
ai
#
database
#
llm
#
rag
Comments
Add Comment
4 min read
What I Actually Pay For When My LLM Bill Doubles Overnight
claire nguyen
claire nguyen
claire nguyen
Follow
May 15
What I Actually Pay For When My LLM Bill Doubles Overnight
#
infrastructure
#
llm
#
devops
#
sre
Comments
Add Comment
4 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