DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Our eval gate runs 22 minutes. The queue behind it hit three hours.

Our eval gate runs 22 minutes. The queue behind it hit three hours.

4
Comments 1
5 min read
Stop Paying for the Same Tokens Twice: A Practical Guide to Prompt Caching

Stop Paying for the Same Tokens Twice: A Practical Guide to Prompt Caching

1
Comments 2
7 min read
Structured output broke on us three times. The third time taught us operator-ready.

Structured output broke on us three times. The third time taught us operator-ready.

Comments
4 min read
LLM-as-a-Judge: Âżpuede reemplazar el criterio de una persona?

LLM-as-a-Judge: Âżpuede reemplazar el criterio de una persona?

Comments
6 min read
Human Approval Gates in the Claude Agent SDK

Human Approval Gates in the Claude Agent SDK

1
Comments 1
3 min read
Trusting an LLM's JSON in production

Trusting an LLM's JSON in production

Comments 2
6 min read
I Tested 7 AI Memory Products for Portability - All 7 Lock You In

I Tested 7 AI Memory Products for Portability - All 7 Lock You In

4
Comments 1
21 min read
I Ditched ChatGPT for Local LLMs and Saved $2,000 in a Year — The Real Numbers

I Ditched ChatGPT for Local LLMs and Saved $2,000 in a Year — The Real Numbers

1
Comments 1
4 min read
OpenAI Just Solved a Problem Open Since 1999. It Still Can't Ask Its Own Question.

Verified by top mathematicians for $2k

OpenAI Just Solved a Problem Open Since 1999. It Still Can't Ask Its Own Question.

25
Comments 14
4 min read
Prompt Engineering Explained Simply: 5 Techniques to Improve Your LLM Outputs

Prompt Engineering Explained Simply: 5 Techniques to Improve Your LLM Outputs

1
Comments
5 min read
Cache Misses — Why Your AI Costs Won’t Drop (Even When Traffic Stays Flat)

Cache Misses — Why Your AI Costs Won’t Drop (Even When Traffic Stays Flat)

1
Comments
2 min read
Low-Cost vs Premium Models: What’s the Real-World Gap?

Low-Cost vs Premium Models: What’s the Real-World Gap?

Comments
1 min read
LLMs locales para agentes de cĂłdigo: lo que YouTube no te cuenta

LLMs locales para agentes de cĂłdigo: lo que YouTube no te cuenta

Comments
3 min read
Cheap Filters First, LLM Last: Running an AI Matcher Inside a Cron Job

Solves explosive LLM costs with boring code

Cheap Filters First, LLM Last: Running an AI Matcher Inside a Cron Job

5
Comments 8
6 min read
Building a Pi Agent from Scratch (7-Day Retrospective)

Building a Pi Agent from Scratch (7-Day Retrospective)

Comments 3
29 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.