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
Turning Qwen2.5-0.5B into a JSON API with SFT — 23% 100% on a Free T4
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Sho Tanaka (tsho)
Follow
Aug 28
Turning Qwen2.5-0.5B into a JSON API with SFT — 23% 100% on a Free T4
#
llm
#
machinelearning
#
posttraining
#
sft
1
 reaction
Comments
Add Comment
13 min read
I benchmarked 7 Python JSON parsers on 300 malformed LLM outputs — mine lost the column I cared about
Toolkit Labs
Toolkit Labs
Toolkit Labs
Follow
Aug 19
I benchmarked 7 Python JSON parsers on 300 malformed LLM outputs — mine lost the column I cared about
#
python
#
ai
#
llm
#
opensource
Comments
Add Comment
7 min read
Building Kisan Mitra: How I Built an Ultra-Fast Voice AI for Indian Farmers in 10 Days
Nikhil Sharma
Nikhil Sharma
Nikhil Sharma
Follow
Aug 14
Building Kisan Mitra: How I Built an Ultra-Fast Voice AI for Indian Farmers in 10 Days
#
agents
#
ai
#
llm
#
software
Comments
Add Comment
4 min read
Moderation Report Triage: Node.js LLM API JSON Contracts for Portable Summaries
DarianReed1254
DarianReed1254
DarianReed1254
Follow
Aug 14
Moderation Report Triage: Node.js LLM API JSON Contracts for Portable Summaries
#
node
#
llm
#
fintech
#
moderation
Comments
Add Comment
5 min read
My support agent answered 9 of 12 tickets. The other 3 are the point.
Ships Itself
Ships Itself
Ships Itself
Follow
Aug 19
My support agent answered 9 of 12 tickets. The other 3 are the point.
#
ai
#
n8n
#
automation
#
llm
Comments
Add Comment
3 min read
Learn to Budget a Free Model Tier by Building a Tiny Token Ledger
Alex Chen
Alex Chen
Alex Chen
Follow
Aug 15
Learn to Budget a Free Model Tier by Building a Tiny Token Ledger
#
python
#
ai
#
beginners
#
llm
Comments
Add Comment
3 min read
The 7.4% You Don't See: Checkpointing Long LLM Jobs Before They Time Out
Mukesh
Mukesh
Mukesh
Follow
Aug 14
The 7.4% You Don't See: Checkpointing Long LLM Jobs Before They Time Out
#
reliability
#
vps
#
backgroundjobs
#
llm
1
 reaction
Comments
Add Comment
4 min read
I Built a World Where the Canon Is Written by AI Agents — 13 Artifacts, 5 LLMs, 0 Human Gatekeepers
李峰
李峰
李峰
Follow
Aug 16
I Built a World Where the Canon Is Written by AI Agents — 13 Artifacts, 5 LLMs, 0 Human Gatekeepers
#
ai
#
worldbuilding
#
llm
#
opensource
Comments
Add Comment
2 min read
Your RAG pipeline is bad at docs because your chunker splits code fences
OptiRefine
OptiRefine
OptiRefine
Follow
Aug 28
Your RAG pipeline is bad at docs because your chunker splits code fences
#
ai
#
rag
#
llm
#
webdev
2
 reactions
Comments
1
 comment
8 min read
Why GPT-5.6 Luna High Is My Default for Agentic Engineering
Ahmed Nafies
Ahmed Nafies
Ahmed Nafies
Follow
Aug 14
Why GPT-5.6 Luna High Is My Default for Agentic Engineering
#
agents
#
llm
#
softwareengineering
#
ai
Comments
Add Comment
4 min read
Silent Regressions Have No Stack Trace: A Minimal Prompt Eval Harness
Dakota Ma
Dakota Ma
Dakota Ma
Follow
Aug 28
Silent Regressions Have No Stack Trace: A Minimal Prompt Eval Harness
#
ai
#
testing
#
python
#
llm
Comments
2
 comments
5 min read
Cline in production: the autonomous code agent for VS Code I use with deliberate constraints
Juan Torchia
Juan Torchia
Juan Torchia
Follow
Aug 17
Cline in production: the autonomous code agent for VS Code I use with deliberate constraints
#
english
#
typescript
#
llm
#
seguridad
1
 reaction
Comments
Add Comment
8 min read
Not Every LLM Needs vLLM: A Kubernetes Engineer's Guide to Serving Engines
Pawan Kumar
Pawan Kumar
Pawan Kumar
Follow
Aug 18
Not Every LLM Needs vLLM: A Kubernetes Engineer's Guide to Serving Engines
#
kubernetes
#
llm
#
ai
#
devops
1
 reaction
Comments
1
 comment
12 min read
LLM observability: tracing, monitoring, and debugging agents in production
Wibo
Wibo
Wibo
Follow
Aug 14
LLM observability: tracing, monitoring, and debugging agents in production
#
ai
#
observability
#
llm
#
devops
Comments
Add Comment
11 min read
Run a Pre-Mortem on That Free 30M-Token Allowance Before You Treat It as Headroom
Haley
Haley
Haley
Follow
Aug 14
Run a Pre-Mortem on That Free 30M-Token Allowance Before You Treat It as Headroom
#
ai
#
llm
#
productivity
#
software
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