close

DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How much does it cost to run a text game with LLMs

Real-world data from 51,000 game API calls
hiper2d profile

How much does it cost to run a text game with LLMs

#ai #llm #gamedev #machinelearning
BERJAYA BERJAYA BERJAYA 25
Comments 27
18 min read
Your LLM returned valid JSON. That doesn't mean it's telling the truth.
soumayaerradi profile

Your LLM returned valid JSON. That doesn't mean it's telling the truth.

#ai #architecture #llm #softwaredevelopment
BERJAYA BERJAYA 5
Picked as gem Comments 5
10 min read
I ran 125 prompt-injection attacks on my AI agent. None got through, and that wasn't the interesting part
riadgaffar profile
Riad

I ran 125 prompt-injection attacks on my AI agent. None got through, and that wasn't the interesting part

#ai #llm #security #python
BERJAYA BERJAYA 4
Comments 23
6 min read
13 papers on AI agent memory: the biggest lesson is to keep the originals
hsin_yenchung_5562e7d5c9 profile

13 papers on AI agent memory: the biggest lesson is to keep the originals

#ai #llm #agents #machinelearning
BERJAYA 2
Comments 5
6 min read
I ranked my AI's memories by age. Every benchmark floor broke.
heinrichneb profile

I ranked my AI's memories by age. Every benchmark floor broke.

#discuss #ai #llm #agents
BERJAYA 1
Comments 1
5 min read
This LLM cost function looks right. Can you spot the bug?
samuel_ochaba_eb9c875fa89 profile

This LLM cost function looks right. Can you spot the bug?

#ai #llm #python #openai
BERJAYA 1
Comments 3
3 min read
Why every AI-built landing page looks the same (and how to stop shipping it)
pich profile

Why every AI-built landing page looks the same (and how to stop shipping it)

#ai #design #llm #webdev
Comments
10 min read
How we stop our AI budgeting coach from making up numbers
danyal_muneer_decd8f77c04 profile

How we stop our AI budgeting coach from making up numbers

#ai #reactnative #llm #fintech
BERJAYA 1
Comments 1
3 min read
What actually survives the OpenAI Evals shutdown, and what you have to rebuild by hand
solocohere profile
Orbora

What actually survives the OpenAI Evals shutdown, and what you have to rebuild by hand

#testing #openai #promptfoo #llm
Comments
3 min read
My Hindsight Debugging Agent Learned to Say "I Don't Know"
deepika_chintamreddy_b528 profile

My Hindsight Debugging Agent Learned to Say "I Don't Know"

#ai #llm #agents #python
Comments
6 min read
How LLMs Create Security Holes (and How to Prevent Them)
greee profile
Greg

How LLMs Create Security Holes (and How to Prevent Them)

#llm #githubcopilot #vscode
Comments
10 min read
I Told Everyone to Tune Voice Agents Per Room. Nine of Mine Share One Config.
nabeelbaghoor profile

I Told Everyone to Tune Voice Agents Per Room. Nine of Mine Share One Config.

#ai #devjournal #testing #llm
Comments
6 min read
A worksheet to compare API bills and self-hosted open models
conorbronsdon profile

A worksheet to compare API bills and self-hosted open models

#ai #llm #opensource #infrastructure
Comments
4 min read
The Sycophancy Bug: How 6 LLMs handle logical pushback (and why reasoning models matter)
bpecha14 profile
Bogdan

The Sycophancy Bug: How 6 LLMs handle logical pushback (and why reasoning models matter)

#discuss #ai #llm #promptengineering
Comments
2 min read
수락 길이는 22.8% 늘었는데 처리량은 14.0%만 늘었습니다: DSpine 카드 수치와 공개 파일 헤더로 투기 디코딩 초안 모델을 읽는 법
vidraft_lab profile

수락 길이는 22.8% 늘었는데 처리량은 14.0%만 늘었습니다: DSpine 카드 수치와 공개 파일 헤더로 투기 디코딩 초안 모델을 읽는 법

#ai #machinelearning #llm #inference
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.