DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
JSON Mode vs. Structured Outputs: Stop LLM App Crashes
nainikmehta profile

JSON Mode vs. Structured Outputs: Stop LLM App Crashes

#llm #ai #json #engineering
1
Comments
3 min read
OpenAI-compatible APIs vs provider abstraction: What actually transfers across LLM providers?
inozem profile

OpenAI-compatible APIs vs provider abstraction: What actually transfers across LLM providers?

#ai #api #llm #openai
Comments 2
7 min read
From Prompt to Platform: How I Would Architect a Production-Grade GPT Application
officialbidisha profile

From Prompt to Platform: How I Would Architect a Production-Grade GPT Application

#architecture #llm #ai #systemdesign
2
Comments 3
15 min read
Letting a local model press the buttons in Pokémon
jackhomer profile

Letting a local model press the buttons in Pokémon

#ai #llm #python #gamedev
Comments
3 min read
I built an epistemic gate to stop LLM data poisoning during fine-tuning. Tested across 5 architectures, orchestrated on a 2006 Toshiba laptop for $0.
dante777 profile

I built an epistemic gate to stop LLM data poisoning during fine-tuning. Tested across 5 architectures, orchestrated on a 2006 Toshiba laptop for $0.

#ai #llm #machinelearning #security
Comments
2 min read
I built an AI API that turns any online store URL into a structured product catalog
crj_787403881c99662c653e8 profile
CRJ

I built an AI API that turns any online store URL into a structured product catalog

#ai #api #llm #saas
Comments
2 min read
Protect Your Users: PII Redaction in AI Requests with Kong AI Gateway 2.0
thegatewayguy profile
Andrew Kew for Kong

Protect Your Users: PII Redaction in AI Requests with Kong AI Gateway 2.0

#ai #llm #security #tutorial
3
Comments 2
15 min read
Bedrock and LangChain disagree on what input_tokens means — never price it without knowing who counted
rdiegoss profile

Bedrock and LangChain disagree on what input_tokens means — never price it without knowing who counted

#bedrock #llm #aws #ai
2
Comments 3
8 min read
typesafe/jev fails on OpenRouter chat/completions: how to call it (and the three response shapes that trip people up)
weirui_chen_48669a172a6be profile

typesafe/jev fails on OpenRouter chat/completions: how to call it (and the three response shapes that trip people up)

#ai #llm #api #openrouter
Comments 3
3 min read
We Tested Our Own AI Safety Checks. They Caught Nothing.
devaland profile

We Tested Our Own AI Safety Checks. They Caught Nothing.

#ai #llm #testing #opensource
Comments 10
5 min read
Build a Hiring Inbox Sorter App with ToolJet MCP and Jev
athulya_r profile

Build a Hiring Inbox Sorter App with ToolJet MCP and Jev

#ai #webdev #software #llm
33
Comments 2
10 min read
60 Subagents, 650 Ideas, One Proof: What Anthropic's Riemann Run Teaches AI Engineers
shivaysinghrajput profile

60 Subagents, 650 Ideas, One Proof: What Anthropic's Riemann Run Teaches AI Engineers

#ai #machinelearning #programming #llm
Comments 2
2 min read
Three token optimizations that made our agent more expensive
qweezyy profile

Three token optimizations that made our agent more expensive

#ai #llm #agents #opensource
3
Comments 7
7 min read
Your Self-Hosted AI Assistant Keeps Forgetting You. Here Is How We Measured a Fix.
neusoftware profile

Your Self-Hosted AI Assistant Keeps Forgetting You. Here Is How We Measured a Fix.

#agents #ai #llm #opensource
Comments 3
4 min read
What an agent loop is (and isn't): state, action, stop
devrchancay profile

What an agent loop is (and isn't): state, action, stop

#agents #agentloop #llm #agentarchitecture
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.