DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Too lazy for Bash: My life with a local AI assistant
codisfy profile

Too lazy for Bash: My life with a local AI assistant

#ai #llm
Comments
2 min read
A New Open-Weight Model Just Dropped? Run This 30-Minute Eval Before You Rewrite Your Pipeline
devrs_886 profile

A New Open-Weight Model Just Dropped? Run This 30-Minute Eval Before You Rewrite Your Pipeline

#ai #opensource #llm #programming
Comments
4 min read
Anthropic desserre les garde-fous biologiques de Fable 5
thibault_monteiro profile

Anthropic desserre les garde-fous biologiques de Fable 5

#ai #claude #llm
Comments
6 min read
Moving Half of Our AI Development to Local LLMs — by Splitting Work by Role, Not by Picking the Biggest Model
uehara profile

Moving Half of Our AI Development to Local LLMs — by Splitting Work by Role, Not by Picking the Biggest Model

#ai #llm #machinelearning #localllm
Comments 2
3 min read
We scanned 383 Show HN products. 27% were unreadable to crawlers, 17% blocked Claude (and nobody wrote that rule)
mike_viewfy profile

We scanned 383 Show HN products. 27% were unreadable to crawlers, 17% blocked Claude (and nobody wrote that rule)

#ai #claude #llm #startup
Comments
5 min read
Testing MCP Servers Used to Be a Pain. Here is How to Test Them with Zero Configuration.
wozaisuzhou profile

Testing MCP Servers Used to Be a Pain. Here is How to Test Them with Zero Configuration.

#ai #llm #mcp #testing
Comments
2 min read
I bootstrapped an API business on a single RTX 3060, from literally zero budget
joaopaulona profile

I bootstrapped an API business on a single RTX 3060, from literally zero budget

#api #buildinpublic #llm #selfhosted
Comments
3 min read
Mi primer intento con agentes de IA fracasĂł. El problema no era el modelo
saulemprendedor profile

Mi primer intento con agentes de IA fracasĂł. El problema no era el modelo

#agents #ai #llm #softwareengineering
Comments
3 min read
Your AI Agent Works in Dev. It Will Fail in Production. Here's the Math.
sasajib profile

Your AI Agent Works in Dev. It Will Fail in Production. Here's the Math.

#ai #llm #devops #agents
Comments
4 min read
A New MiniMax Model Dropped: How to Evaluate It on Your Own Code Before Believing the Benchmarks
apppro_5726 profile

A New MiniMax Model Dropped: How to Evaluate It on Your Own Code Before Believing the Benchmarks

#ai #opensource #llm #programming
Comments
4 min read
Programmatic SEO in 2026: How to Scale by Role and Market for AI Search (AEO)
mdabir1203 profile

Programmatic SEO in 2026: How to Scale by Role and Market for AI Search (AEO)

#ai #llm #seo
Comments
5 min read
Vector Search Fundamentals for RAG Design: ANN (HNSW), Distance Metrics, Metadata Filtering, and BM25
hiroki-kameyama profile

Vector Search Fundamentals for RAG Design: ANN (HNSW), Distance Metrics, Metadata Filtering, and BM25

#rag #vectorsearch #hnsw #llm
Comments 1
5 min read
Phase 7b — Bolting On the AI: An LLMCategorizer Behind the Same Door (with Caching, a Fallback, and Six Model Names)
silentcarry profile

Phase 7b — Bolting On the AI: An LLMCategorizer Behind the Same Door (with Caching, a Fallback, and Six Model Names)

#ai #architecture #llm #python
Comments 1
12 min read
Last week I checked the exact-match .cn domains for eight international B2B work-management brands.
visibilityatlas profile

Last week I checked the exact-match .cn domains for eight international B2B work-management brands.

#ai #llm #seo #webdev
Comments 1
3 min read
Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.
tommy_leonhardsen_81d1f4e profile

Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

#llm #benchmarks #reasoning #latency
1
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.