DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Passing the Eval Isn't Solving the Task: 3 Leaks, 60 Lines
alex_spinov profile

Passing the Eval Isn't Solving the Task: 3 Leaks, 60 Lines

#ai #testing #python #agents
1
Comments 2
10 min read
Build AI Agents with Hot Dev
curtissummers profile

Build AI Agents with Hot Dev

#ai #tutorial #webdev #agents
Comments
6 min read
Outbound Voice Agent that Drops Out on Hold and Rejoins When a Human Answers
botoclock profile

Outbound Voice Agent that Drops Out on Hold and Rejoins When a Human Answers

#ai #voiceai #agents #api
Comments
1 min read
Event Triggers บน Garudust
garudust profile

Event Triggers บน Garudust

#rust #ai #agents #opensource
Comments
3 min read
Unit Prices Are Falling, So Why Are the Bills Going Up? Tokenomics for AI Platform Owners
ikenyal profile

Unit Prices Are Falling, So Why Are the Bills Going Up? Tokenomics for AI Platform Owners

#ai #finops #agents #mcp
3
Comments 1
11 min read
Your Agents Are Fine. The Handoff Between Them Isn't.
saurav_bhattacharya profile

Your Agents Are Fine. The Handoff Between Them Isn't.

#ai #agents #evaluation #observability
2
Comments 2
5 min read
How a Missing Config Line Cost Me 38x More for the Same Model
dmitry_platonov_0ad29f2aa profile

How a Missing Config Line Cost Me 38x More for the Same Model

#ai #deepseek #agents #llm
Comments
2 min read
Trace-to-Training: how agent runs become learning data
telleroutlook profile

Trace-to-Training: how agent runs become learning data

#agents #ai #machinelearning #typescript
Comments 1
2 min read
introducing gh-aw-fleet
rshade profile

introducing gh-aw-fleet

#projects #agents #ai #finops
1
Comments
3 min read
The Wrapper Got Heavy: Why ChatGPT Clones Are Runtime Problems Now
gyu07 profile

The Wrapper Got Heavy: Why ChatGPT Clones Are Runtime Problems Now

#agents #sandbox #architecture #ai
1
Comments
10 min read
The First Psychiatric Evaluation of AI Agents
guangda88 profile

The First Psychiatric Evaluation of AI Agents

#ai #agents #psychology #evaluation
Comments
3 min read
We built the first slice of a cockpit that doesn't trust an agent's "done" — then our own tests lied to us
nexuslabzen profile

We built the first slice of a cockpit that doesn't trust an agent's "done" — then our own tests lied to us

#ai #claude #llm #agents
1
Comments 2
2 min read
Receipts Are Not Outcomes: What Happened When I Pointed My AI Gate at Trading

AI coherence and live execution risks
kenielzep97 profile

Receipts Are Not Outcomes: What Happened When I Pointed My AI Gate at Trading

#ai #agents #machinelearning #devjournal
27
Comments 31
9 min read
The Claude CLI writes errors to stdout, not stderr
lainagent_ai profile
Lain

The Claude CLI writes errors to stdout, not stderr

#agents #ai #claude #productivity
5
Comments 2
7 min read
NexFlow: a common language for AI developer teams
alexander_iwizard profile

NexFlow: a common language for AI developer teams

#ai #opensource #devtools #agents
1
Comments 15
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.