DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Fine-Tuning Phi-3 & Gemma 2: The Budget Path to GPT-4 Performance at a Fraction of the Cost

Fine-Tuning Phi-3 & Gemma 2: The Budget Path to GPT-4 Performance at a Fraction of the Cost

Comments
14 min read
I let my AI agent read a file. It tried to leak my credentials.

I let my AI agent read a file. It tried to leak my credentials.

1
Comments
4 min read
Building a Multi-Agent AI Forecasting System: Architecture Deep Dive

Building a Multi-Agent AI Forecasting System: Architecture Deep Dive

1
Comments
5 min read
How to Reduce LLM Token Usage Without Losing Context

How to Reduce LLM Token Usage Without Losing Context

4
Comments 2
4 min read
把治理账本当作控制平面:多 Agent 时代的收敛核心

把治理账本当作控制平面:多 Agent 时代的收敛核心

Comments
1 min read
AI Development Tools Every Engineering Team Needs in 2026

AI Development Tools Every Engineering Team Needs in 2026

Comments
5 min read
LangChain vs LlamaIndex in 2026: What We Actually Use and Why

LangChain vs LlamaIndex in 2026: What We Actually Use and Why

2
Comments
4 min read
Why Falling AI Token Prices Don’t Mean Lower Costs

Why Falling AI Token Prices Don’t Mean Lower Costs

1
Comments
5 min read
Real LLM Drift Detection Results: Exact Outputs, Real Scores, No Fabrication

Real LLM Drift Detection Results: Exact Outputs, Real Scores, No Fabrication

Comments
3 min read
I ran 5 social engineering attacks on AI. The failure modes are human.

I ran 5 social engineering attacks on AI. The failure modes are human.

1
Comments
2 min read
Self-Hosted Email Threat Detection: Real-Time Monitoring, Multi-Stage Enrichment, and LLM Verdicts with Legal Compliance

Self-Hosted Email Threat Detection: Real-Time Monitoring, Multi-Stage Enrichment, and LLM Verdicts with Legal Compliance

1
Comments
15 min read
Anthropic Silently Dropped Prompt Cache TTL from 1 Hour to 5 Minutes

Anthropic Silently Dropped Prompt Cache TTL from 1 Hour to 5 Minutes

Comments
3 min read
Addressing LLM Benchmarking Obsolescence: Strategies for Timely and Relevant Model Evaluation

Addressing LLM Benchmarking Obsolescence: Strategies for Timely and Relevant Model Evaluation

1
Comments
13 min read
The "Always" Trap: Why Your AI Ignores Nuance (And How to Fix It)

The "Always" Trap: Why Your AI Ignores Nuance (And How to Fix It)

1
Comments
7 min read
AI개인화_블로그글

AI개인화_블로그글

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