DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why more context makes your AI answers worse
vladut02 profile
VLAD

Why more context makes your AI answers worse

#ai #llm #promptengineering #machinelearning
Comments
4 min read
Agentic Localization, Low to no cost for tokens.
harmanpreetsingh profile

Agentic Localization, Low to no cost for tokens.

#agents #ai #architecture #llm
Comments 1
4 min read
What Is LLM Actually Doing? A Fellow Engineer's Take on Vectors, Next-Token Prediction, and Fail-back Routing
dev_next4i profile

What Is LLM Actually Doing? A Fellow Engineer's Take on Vectors, Next-Token Prediction, and Fail-back Routing

#llm #buildinpublic #next4i #architecture
Comments
4 min read
"Multi-Agent" Is Often a Single Agent: What 86 Repos Actually Implement
howcani_howcani_77e786a89 profile

"Multi-Agent" Is Often a Single Agent: What 86 Repos Actually Implement

#ai #agents #llm
1
Comments
2 min read
Billing LLM usage per token: the pitfalls nobody warns you about
kral-ai profile

Billing LLM usage per token: the pitfalls nobody warns you about

#ai #architecture #llm #backend
Comments
2 min read
From Software Engineer to AI Engineer - Part 4: RAG-ing the facts
bjornvdlaan profile

From Software Engineer to AI Engineer - Part 4: RAG-ing the facts

#ai #llm #rag #softwareengineering
Comments
9 min read
Is an AI Product Still the Same After Its AI Layer Changes?
raicho_minev_f7f6baf70d35 profile

Is an AI Product Still the Same After Its AI Layer Changes?

#discuss #ai #llm #testing
Comments
1 min read
Anthropic + Nvidia: The $35B AI Cloud Shift
gp-ia-blog profile

Anthropic + Nvidia: The $35B AI Cloud Shift

#news #ai #machinelearning #llm
Comments 1
9 min read
Spark X2.5-4B & 1.7B: the only on-device models with native 1M-token context — now open source
sparkllm profile

Spark X2.5-4B & 1.7B: the only on-device models with native 1M-token context — now open source

#opensource #llm #edgeai #ondevice
Comments
2 min read
Your Agent Has Tools Now: Why MCP Tool Calls Need Runtime Verification
correctover profile

Your Agent Has Tools Now: Why MCP Tool Calls Need Runtime Verification

#mcp #aiagents #security #llm
1
Comments
6 min read
An AWS Labs agent-eval sample uses the same model as judge and subject
michael_hurst_c009b1bdeb8 profile

An AWS Labs agent-eval sample uses the same model as judge and subject

#ai #llm #testing #opensource
Comments 2
3 min read
Chronos: Building a Governed AI Control Plane Where Production Wipes Are Structurally Impossible
oladimeji_suraju_bc7be040 profile

Chronos: Building a Governed AI Control Plane Where Production Wipes Are Structurally Impossible

#agents #ai #go #llm
Comments 1
3 min read
RDAI: A Multi-Brain Python SDK for Self-Healing AI
ranajit-dhar-dev profile

RDAI: A Multi-Brain Python SDK for Self-Healing AI

#python #ai #opensource #llm
3
Comments
7 min read
The Free Model Kept Explaining an Outage That Already Ended: 48 Hours of Context-Budget Field Notes
codepy_1473 profile

The Free Model Kept Explaining an Outage That Already Ended: 48 Hours of Context-Budget Field Notes

#ai #python #devops #llm
Comments
4 min read
Will software ever be free?
panuhorsmalahti profile

Will software ever be free?

#ai #llm #software
3
Comments 1
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.