DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Building a Production LLM Evaluation Harness in Pytest: Cost-Bounded, Flake-Aware, CI-Gated (Runnable Python)
velsof profile

Building a Production LLM Evaluation Harness in Pytest: Cost-Bounded, Flake-Aware, CI-Gated (Runnable Python)

#python #llm #testing #ai
Comments
9 min read
AgentLiar Detector: Catch Coding Agents That Falsely Claim Task Completion
nilofer_tweets profile

AgentLiar Detector: Catch Coding Agents That Falsely Claim Task Completion

#agents #machinelearning #llm #opensource
9
Comments 2
5 min read
# What LoRA Actually Adapts and Why Higher Rank Doesn't Always Buy What It Looks Like It Should Explainer by: Eyoel Nebiyu
eyorata profile

# What LoRA Actually Adapts and Why Higher Rank Doesn't Always Buy What It Looks Like It Should Explainer by: Eyoel Nebiyu

#deeplearning #llm #machinelearning #tutorial
Comments
5 min read
llama.cpp supports Sparse MoE, new Qwen3.6 GGUF, & WebWorld for local agents
soytuber profile
soy

llama.cpp supports Sparse MoE, new Qwen3.6 GGUF, & WebWorld for local agents

#ai #llm #selfhosted
Comments
3 min read
I tracked 332 AI releases this week. 85% were noise.
alexmorgan_finwriter profile

I tracked 332 AI releases this week. 85% were noise.

#ai #buildinpublic #llm
Comments
2 min read
Ollama Cloud Free vs Pro — Usage Limits, Pricing & What You Actually Get (2026)
amareswer profile

Ollama Cloud Free vs Pro — Usage Limits, Pricing & What You Actually Get (2026)

#ollama #ai #llm #devops
Comments 1
3 min read
AI API Cost Caps and Multi-Key Failover: The Boring Layer That Matters
jm_ij_5e20a7a0dfb0ac1970e profile

AI API Cost Caps and Multi-Key Failover: The Boring Layer That Matters

#ai #api #infrastructure #llm
1
Comments
1 min read
Documents are records waiting to exist
bimbobruno profile

Documents are records waiting to exist

#ai #data #llm #rag
Comments
2 min read
Tool Definition Drift: When Your Agent's Toolset Outgrows Its Prompt
gabrielanhaia profile

Tool Definition Drift: When Your Agent's Toolset Outgrows Its Prompt

#ai #llm #agents #promptengineering
Comments
8 min read
Most AI "Hallucinations" Are Context Failures, Not Model Failures
martinlepage26bit profile

Most AI "Hallucinations" Are Context Failures, Not Model Failures

#discuss #ai #llm #machinelearning
Comments
4 min read
Modelos Antigravity (Maio 2026)
danielaccorsi profile

Modelos Antigravity (Maio 2026)

#agents #ai #google #llm
1
Comments
4 min read
Did My LoRA Learn Tenacious Style—or Just Memorize Augmented Patterns?
bnobody47 profile

Did My LoRA Learn Tenacious Style—or Just Memorize Augmented Patterns?

#deeplearning #llm #machinelearning #nlp
Comments
3 min read
Set Up Your Own ChatGPT: Ollama + Open WebUI for Data That Never
merbayerp profile

Set Up Your Own ChatGPT: Ollama + Open WebUI for Data That Never

#llm #guide #software
Comments
10 min read
Beyond the Hype: A Comprehensive Guide to Benchmarking LLMs with AWS Labs’ LLMeter
qainsights profile

Beyond the Hype: A Comprehensive Guide to Benchmarking LLMs with AWS Labs’ LLMeter

#ai #testing #performance #llm
5
Comments
6 min read
The 50,000-Token Demonstration Nobody Saved: Capturing Agent Trajectories to Train Your Own Code-SLM
alex_chen_45b61c234682eb6 profile

The 50,000-Token Demonstration Nobody Saved: Capturing Agent Trajectories to Train Your Own Code-SLM

#agents #claude #llm #softwareengineering
Comments
14 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.