DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How AI Voice Agents Actually Work
miragecloud profile

How AI Voice Agents Actually Work

#agents #ai #llm
Comments 1
4 min read
67 Lines of Bash That Won't Let an LLM Say Done: A Stop Hook That Reads the Transcript JSONL
bokuwalily profile
Lily

67 Lines of Bash That Won't Let an LLM Say Done: A Stop Hook That Reads the Transcript JSONL

#claudecode #automation #llm #shell
1
Comments
21 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
OKF Agent Memory: give your coding agents a git-native memory that survives every session
aifrontierpost profile

OKF Agent Memory: give your coding agents a git-native memory that survives every session

#ai #llm #machinelearning #tutorial
1
Comments 2
10 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
Bonsai 2 27B Puts a 27B AI Model in 5.9GB - Can It Replace Your Paid Subscription?
jamilxt profile

Bonsai 2 27B Puts a 27B AI Model in 5.9GB - Can It Replace Your Paid Subscription?

#ai #localai #llm #machinelearning
4
Comments 2
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
Three layers of automated fact-checking for an LLM newsroom (and the bugs that forced each one)
presentofai profile

Three layers of automated fact-checking for an LLM newsroom (and the bugs that forced each one)

#agents #ai #architecture #llm
Comments 1
3 min read
$402 on one ticket: cost per turn in headless Claude Code
panthpatel profile

$402 on one ticket: cost per turn in headless Claude Code

#ai #claudecode #llm #finops
1
Comments 5
4 min read
How We Built a 99.9% Uptime Multi-Model AI Router (Claude -> GPT-4o -> DeepSeek) in n8n Without SaaS Middleware
ancucorp profile

How We Built a 99.9% Uptime Multi-Model AI Router (Claude -> GPT-4o -> DeepSeek) in n8n Without SaaS Middleware

#ai #architecture #automation #llm
2
Comments 1
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
AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract
mech_app_ai profile

AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract

#agents #ai #aws #llm
1
Comments
6 min read
From RLHF to RLVR: The Evolution of Reward Signals and the Battle Against Reward Hacking
gfactor profile

From RLHF to RLVR: The Evolution of Reward Signals and the Battle Against Reward Hacking

#machinelearning #reinforcementlearning #llm #security
Comments 1
9 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
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.