DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Reasoning Ledger: Remembering Decisions, Not Just Data

Git analogy clarifies agent memory gaps
kenwalger profile

The Reasoning Ledger: Remembering Decisions, Not Just Data

#ai #agents #llm #architecture
54
Comments 62
4 min read
Teaching an Audio Model More About Barbados
hammertoe profile

Teaching an Audio Model More About Barbados

#ai #barbados #llm #machinelearning
Comments
15 min read
Standing Up a GPU Cluster on AKS for vLLM
josef_doornink_930b2caf1c profile

Standing Up a GPU Cluster on AKS for vLLM

#azure #devops #kubernetes #llm
Comments
9 min read
Upgrading the judge ends one score series and starts another
maya_andersson_dev profile

Upgrading the judge ends one score series and starts another

#llm #statistics #datascience #testing
5
Comments
9 min read
# I benchmarked AI agent memory in 2026 — and the numbers tell a different story than the marketing
everest_an profile

# I benchmarked AI agent memory in 2026 — and the numbers tell a different story than the marketing

#agents #ai #llm #testing
Comments
4 min read
How Claude Marks AI-Generated Content?
hassann profile

How Claude Marks AI-Generated Content?

#ai #claude #llm #security
Comments 1
9 min read
Stop Building AI Wrappers. Start Building AI Systems
shourya_kumar profile

Stop Building AI Wrappers. Start Building AI Systems

#ai #api #llm #agents
Comments
2 min read
A Reader Audited My OSS Release in Public. He Found the Contradictions I Missed.
debashish_ghosal profile

A Reader Audited My OSS Release in Public. He Found the Contradictions I Missed.

#ai #planner #llm #testing
18
Comments 8
7 min read
The Best Model Pair in My Field Test Was Also the Least Trustworthy
debashish_ghosal profile

The Best Model Pair in My Field Test Was Also the Least Trustworthy

#healthydebate #ai #trustworthy #llm
22
Comments 7
12 min read
I benchmarked 8 LLMs for a niche production app. The flagship cost 5.8x more - and lost.
shanni profile

I benchmarked 8 LLMs for a niche production app. The flagship cost 5.8x more - and lost.

#llm #ai #typescript #webdev
2
Comments 3
5 min read
Your AI Scam Detector Trusts Fake Reviewers More Than You Think
coridev profile
Cor E

Your AI Scam Detector Trusts Fake Reviewers More Than You Think

#security #ai #llm #appsec
1
Comments
3 min read
Running a Local LLM Proxy: OpenAI-Compatible Gateways
3ni8ma profile

Running a Local LLM Proxy: OpenAI-Compatible Gateways

#llm #api #proxy #localai
1
Comments
2 min read
AI agent security: a threat model for autonomous agents
weston_carnes_d580b505e0c profile

AI agent security: a threat model for autonomous agents

#ai #security #llm #devops
Comments 1
2 min read
The pleasing effect: why AI grades your CV on a curve
therabbithole profile

The pleasing effect: why AI grades your CV on a curve

#ai #career #llm #promptengineering
Comments
6 min read
ResKV: Recovering Evicted Token Contributions via Residual KV Cache — LongBench 32/32
cofldus profile

ResKV: Recovering Evicted Token Contributions via Residual KV Cache — LongBench 32/32

#llm #machinelearning #performance #pytorch
Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.