DEV Community

#latency

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Best-of-N is prepaid retries: the cost math of racing parallel attempts

Best-of-N is prepaid retries: the cost math of racing parallel attempts

Comments
5 min read
Your token bill is the cheap part: dimensioning the real cost of an agent

Your token bill is the cheap part: dimensioning the real cost of an agent

Comments
7 min read
Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

1
Comments
8 min read
How I tried to write an article about slow Chinese LLMs

How I tried to write an article about slow Chinese LLMs

17
Comments 16
10 min read
How Fast Should Your AI Voice Agent Respond?

How Fast Should Your AI Voice Agent Respond?

2
Comments 2
4 min read
The 50ms promise I made in v1.6

The 50ms promise I made in v1.6

Comments
5 min read
Putting Prism's front door on every continent

Putting Prism's front door on every continent

Comments
6 min read
A voice agent is not a chatbot with a phone number

A voice agent is not a chatbot with a phone number

2
Comments 1
9 min read
How we slashed an AI Agent's latency by 80% in 60 minutes

How we slashed an AI Agent's latency by 80% in 60 minutes

12
Comments 1
1 min read
The caller heard silence for two seconds before the agent spoke

The caller heard silence for two seconds before the agent spoke

Comments
6 min read
5 LLM APIs Tested for Latency: Real Data [2026]

5 LLM APIs Tested for Latency: Real Data [2026]

Comments 1
13 min read
Building Low-Latency Trading Bots: Architecting Real-Time WebSocket Streams

Building Low-Latency Trading Bots: Architecting Real-Time WebSocket Streams

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