close

DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Embeddings Cannot Say No: An Intent Detector's Real Numbers
julesrobineau profile

Embeddings Cannot Say No: An Intent Detector's Real Numbers

#machinelearning #ai #nlp #llm
1
Comments
5 min read
How LangChain extracted value out of their own agents
midnqp profile

How LangChain extracted value out of their own agents

#agents #ai #llm #productivity
Comments
1 min read
Node.js API Key Text Classification: JSON Validation Before Multi-Provider Gateway Failover
oberonjohansson6982 profile

Node.js API Key Text Classification: JSON Validation Before Multi-Provider Gateway Failover

#node #llm #typescript
Comments
6 min read
Adding Responses API to an Agent Framework
humzakt profile

Adding Responses API to an Agent Framework

#responsesapi #openai #llm #agentframework
Comments
6 min read
A judge that agrees with your humans 92 percent of the time can be at 60 percent where the gate actually decides
maya_andersson_dev profile

A judge that agrees with your humans 92 percent of the time can be at 60 percent where the gate actually decides

#llm #statistics #testing #datascience
Comments
8 min read
The Model Reading My Benchmark Mattered More Than the Memory System Did
spranab profile

The Model Reading My Benchmark Mattered More Than the Memory System Did

#ai #llm #benchmarking #opensource
Comments
7 min read
Guard Implementation Patterns to Stop AI Agent Runaway Behavior — 7 Types Extracted from Real-World Logs
orca_forge profile

Guard Implementation Patterns to Stop AI Agent Runaway Behavior — 7 Types Extracted from Real-World Logs

#ai #toolcalling #llm #computeruse
Comments
5 min read
Testing OmniRoute locally: verify your AI gateway actually works before you trust it
ahmed_nafies_3a55c907115c profile

Testing OmniRoute locally: verify your AI gateway actually works before you trust it

#ai #api #llm #testing
Comments
4 min read
Did FP8 make the model dumber? A per-prompt regression check for quantized serving
conatusai profile
Jahn

Did FP8 make the model dumber? A per-prompt regression check for quantized serving

#llm #machinelearning #performance #python
Comments
3 min read
A Better FP4 Gradient Quantizer That Training Couldn't Notice
megapixel99 profile

A Better FP4 Gradient Quantizer That Training Couldn't Notice

#llm #measurement #quantization #training
Comments
7 min read
Claude Opus 5 Is Too Good to Stay in a Browser—Put It in Discord, Slack, Telegram & LINE
rockchinq profile
Rock

Claude Opus 5 Is Too Good to Stay in a Browser—Put It in Discord, Slack, Telegram & LINE

#ai #tutorial #opensource #llm
1
Comments
3 min read
Needle 2: the 14 MB agentic model, tested properly
cognitalk profile

Needle 2: the 14 MB agentic model, tested properly

#agents #ai #llm #machinelearning
1
Comments
1 min read
Computer use leaves beta, request shape changes — the weekly AI engineering brief
aiarch_wibo profile
Wibo

Computer use leaves beta, request shape changes — the weekly AI engineering brief

#news #ai #llm #engineering
Comments
6 min read
How I Built a Reliable LLM Pipeline for Ad Creative Evaluation (with Strict Pydantic Contracts)
strelok25dev profile

How I Built a Reliable LLM Pipeline for Ad Creative Evaluation (with Strict Pydantic Contracts)

#python #llm #pydantic #ai
1
Comments 1
3 min read
Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model
felipe0liveira profile

Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

#agents #ai #llm #softwareengineering
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.