DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Verdict: Evidence-First Agent Harness for Reproducible Bug Fixes
mech_app_ai profile

Verdict: Evidence-First Agent Harness for Reproducible Bug Fixes

#agents #debugging #llm #testing
Comments
5 min read
Persona-Execution Separation: Why Governed AI Agents Need Two Trust Domains
mech_app_ai profile

Persona-Execution Separation: Why Governed AI Agents Need Two Trust Domains

#agents #ai #architecture #llm
Comments
5 min read
Commit the Conversation: Keep Partial Voice Turns Out of Your AI Companion’s Context
susiewang profile

Commit the Conversation: Keep Partial Voice Turns Out of Your AI Companion’s Context

#ai #architecture #llm #typescript
Comments
9 min read
The verdict that survived its own correction
thekilteddev profile

The verdict that survived its own correction

#localmodels #llm #softwareengineering #buildinpublic
Comments
7 min read
Teaching an LLM to pull MCP Resources and Prompts on demand (instead of drowning it in context)
anirbaan_chowdhury_58a600 profile

Teaching an LLM to pull MCP Resources and Prompts on demand (instead of drowning it in context)

#ai #mcp #llm #python
Comments
7 min read
Getting Agents to Stop Assuming: What a First AWS Agent Workflow Reveals About Constraint Design
mech_app_ai profile

Getting Agents to Stop Assuming: What a First AWS Agent Workflow Reveals About Constraint Design

#agents #ai #aws #llm
1
Comments
6 min read
I built an epistemic gate to stop LLM data poisoning during fine-tuning. Tested across 5 architectures, orchestrated on a 2006 Toshiba laptop for $0.
dante777 profile

I built an epistemic gate to stop LLM data poisoning during fine-tuning. Tested across 5 architectures, orchestrated on a 2006 Toshiba laptop for $0.

#ai #opensource #machinelearning #llm
1
Comments 3
2 min read
llama-server's sleep mode loses or crashes on a request that arrives just before it sleeps
homelabpm profile

llama-server's sleep mode loses or crashes on a request that arrives just before it sleeps

#llm #llamacpp #selfhosted #debugging
1
Comments 2
7 min read
Fine-tuning a 7B model needs 112 GB. The model is only 14 GB of it.
narotra05hp profile

Fine-tuning a 7B model needs 112 GB. The model is only 14 GB of it.

#machinelearning #llm #ai #deeplearning
1
Comments 1
3 min read
API deprecation for AI models: what breaks when a model is retired
axrisi profile

API deprecation for AI models: what breaks when a model is retired

#ai #api #llm #openai
2
Comments 1
9 min read
I Benchmarked 4 Frontier LLMs on Catching ML's "Silent Killers" — DeepSeek-R1 Missed the Most Basic Bug

Kaggle Benchmarking Challenge Submission
balaji75 profile

I Benchmarked 4 Frontier LLMs on Catching ML's "Silent Killers" — DeepSeek-R1 Missed the Most Basic Bug

#ai #machinelearning #llm
1
Comments 1
3 min read
Inside My llama.cpp Setup: Tuning Qwen 3.8 27B for 512K Context
dmitryame profile

Inside My llama.cpp Setup: Tuning Qwen 3.8 27B for 512K Context

#ai #llm #localllm #llamacpp
2
Comments 3
7 min read
Designing an eval harness for prompt-injection detection: what measuring my defenses actually taught me
shaarkymoo profile

Designing an eval harness for prompt-injection detection: what measuring my defenses actually taught me

#ai #security #llm #python
Comments 1
6 min read
System design for physical AI: a fully air-gapped stack for an oil and gas operation in Pakistan
umar_bilal_fd6e1f54398cec profile

System design for physical AI: a fully air-gapped stack for an oil and gas operation in Pakistan

#ai #llm #selfhosted #architecture
1
Comments
4 min read
LLM Observability & Evaluation Tools: A Practical Guide for Small Teams
julianros profile

LLM Observability & Evaluation Tools: A Practical Guide for Small Teams

#llm #observability #devops #ai
Comments 2
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.