DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Multi-Agent Orchestration Is Harder Than It Looks
sahajmeet_kaur_ profile

Why Multi-Agent Orchestration Is Harder Than It Looks

#ai #agents #mlops #llm
1
Comments
8 min read
Why similarity matters more than exact matches in LLM systems
joshua_chukwu_ccb92f05a94 profile

Why similarity matters more than exact matches in LLM systems

#ai #llm #performance #systemdesign
Comments
3 min read
29/60 Days System Design Questions
thejoud1997 profile

29/60 Days System Design Questions

#ai #agentaichallenge #systemdesign #llm
2
Comments 4
1 min read
Google's I/O 2024 announcements just reset the AI developer stack
albertomontagnese profile

Google's I/O 2024 announcements just reset the AI developer stack

#ai #llm #machinelearning #devtools
1
Comments 1
3 min read
Chaos testing your CI runner fleet when half the jobs call an LLM
claire_nguyen profile

Chaos testing your CI runner fleet when half the jobs call an LLM

#devops #sre #infrastructure #llm
Comments 1
4 min read
The Discipline Nobody Teaches AI Agents: Context Engineering
mrclaw207 profile

The Discipline Nobody Teaches AI Agents: Context Engineering

#agents #ai #llm #performance
1
Comments
4 min read
Debugging Distributed Systems: The Pain of Deterministic AllReduce
tracepilot_2841f1db6718a1 profile

Debugging Distributed Systems: The Pain of Deterministic AllReduce

#ai #debugging #llm #observability
Comments
3 min read
Limites de Taxa da API GPT: NĂ­veis, Limites de Uso e Como Testar com Apidog
lucas_ferreira profile

Limites de Taxa da API GPT: NĂ­veis, Limites de Uso e Como Testar com Apidog

#api #llm #openai #testing
1
Comments
10 min read
Store the proof, not the moral
agentmemory-dev profile

Store the proof, not the moral

#ai #llm #agents #fsc1
1
Comments
4 min read
You're probably using AI wrong. And it's costing you more than you think.
jinav_shah_6c63fcc03c0b9e profile

You're probably using AI wrong. And it's costing you more than you think.

#llm #ai #machinelearning #architecture
Comments
4 min read
KI in KMU's
brodrigues687stack profile

KI in KMU's

#agents #ai #llm #startup
Comments
1 min read
I tried to break my own MCP prompt-injection detector. One class of attack walks straight through - and it isn't a bug.
churik5 profile

I tried to break my own MCP prompt-injection detector. One class of attack walks straight through - and it isn't a bug.

#security #ai #llm #mcp
3
Comments 9
6 min read
Treat upstream catalogs as mutable: how a free-tier model SKU retirement broke my AI agent
k08200 profile

Treat upstream catalogs as mutable: how a free-tier model SKU retirement broke my AI agent

#ai #llm #webdev #infrastructure
3
Comments 32
3 min read
Your prompt is getting longer without you knowing it (and it's killing your margins)
amedinat profile

Your prompt is getting longer without you knowing it (and it's killing your margins)

#ai #llm #productivity #programming
Comments
2 min read
llama.cpp Gains llama-eval, MagicQuant v2.0 for GGUF, Needle 26M Tool Model Released
soytuber profile
soy

llama.cpp Gains llama-eval, MagicQuant v2.0 for GGUF, Needle 26M Tool Model Released

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