close

DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The AI Exam Author Was Never Wrong. I Still Can't Use Its Exam.
ramses203 profile

The AI Exam Author Was Never Wrong. I Still Can't Use Its Exam.

#ai #llm #testing #programming
2
Comments 2
4 min read
Context Drift on a Free Server: A Reproducible Memory Stress Test
codejs_6920 profile

Context Drift on a Free Server: A Reproducible Memory Stress Test

#ai #testing #llm #typescript
Comments
4 min read
Free AI Servers Are a Constraint, Not a Gift: A Reproducible Evaluation
hackjs_8688 profile

Free AI Servers Are a Constraint, Not a Gift: A Reproducible Evaluation

#ai #llm #agents #opensource
Comments
5 min read
An Agent on a Leash, or why my AI agent doesn't make business decisions
tonal profile

An Agent on a Leash, or why my AI agent doesn't make business decisions

#java #ai #llm #agents
Comments 2
6 min read
Free Endpoints Are a Contract, Not a Gift: A Fit Test for Agent Workloads
codepro_3283 profile

Free Endpoints Are a Contract, Not a Gift: A Fit Test for Agent Workloads

#ai #programming #llm #opensource
Comments 1
5 min read
The loop your agent can't see
dibyanshu_kumar profile

The loop your agent can't see

#ai #llm #softwareengineering #contextrot
Comments
6 min read
Free AI Servers Are a Trap Until You Meter Them
techpy_768 profile

Free AI Servers Are a Trap Until You Meter Them

#ai #python #opensource #llm
1
Comments
5 min read
Free Tokens, Paid Verification: A Cost-Per-Compile Gauntlet for MonkeyCode's Free Tier
datacpp_3670 profile

Free Tokens, Paid Verification: A Cost-Per-Compile Gauntlet for MonkeyCode's Free Tier

#c #ai #testing #llm
1
Comments
4 min read
Domux: a compact open model for smart-home command understanding at the edge
sparkllm profile

Domux: a compact open model for smart-home command understanding at the edge

#opensource #llm #edgeai #smarthome
Comments
1 min read
Debugging a Flaky LLM Pipeline: Timeouts, Truncation, and a 40-Line Probe
datago_8008 profile

Debugging a Flaky LLM Pipeline: Timeouts, Truncation, and a 40-Line Probe

#llm #debugging #python #ai
Comments
5 min read
DeepSeek Harness: When the Agent Runtime Becomes the Product
mech_app_ai profile

DeepSeek Harness: When the Agent Runtime Becomes the Product

#agents #ai #architecture #llm
Comments
6 min read
Agent Memory Poisoning: Why Content Screening and Provenance Ranking Can't Stop Persistent False Information
mech_app_ai profile

Agent Memory Poisoning: Why Content Screening and Provenance Ranking Can't Stop Persistent False Information

#agents #ai #llm #security
Comments
4 min read
One Project Ate the Shared Free Tier: A Per-Project Quota Pattern for LLM Gateways
codepro_9661 profile

One Project Ate the Shared Free Tier: A Per-Project Quota Pattern for LLM Gateways

#ai #llm #architecture #python
Comments
4 min read
Claude Code's ELI5 Skill Explained: How It Works, Setup, and When to Use It
gridport profile

Claude Code's ELI5 Skill Explained: How It Works, Setup, and When to Use It

#claudecode #ai #productivity #llm
1
Comments
4 min read
Steal This Exam. Here's How to Port It to Your Own Pipeline.
ramses203 profile

Steal This Exam. Here's How to Port It to Your Own Pipeline.

#ai #llm #testing #programming
3
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.