DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I built a pricing API for LLMs — then realized the real users might not be human
adrasmussen profile

I built a pricing API for LLMs — then realized the real users might not be human

#ai #api #llm #software
Comments 1
3 min read
Ecommerce Product Decisions in Node.js: LLM Contracts for Exact JSON Labels
caderaven6851 profile

Ecommerce Product Decisions in Node.js: LLM Contracts for Exact JSON Labels

#node #llm #ecommerce
Comments
5 min read
Most AI Second Opinions Are Fake. I Built a Two-LLM Review Engine to Prove It.

Tested on 70 real PRs for just $0.53 total cost
debashish_ghosal profile

Most AI Second Opinions Are Fake. I Built a Two-LLM Review Engine to Prove It.

#ai #adversarial #llm #testing
17
Comments 12
11 min read
Direct LLM API Failure Boundaries: SaaS Token Cost and Fallback
dawnli2026 profile

Direct LLM API Failure Boundaries: SaaS Token Cost and Fallback

#llm #saas #architecture
Comments
6 min read
The 6-Line Fix That Outperformed My Entire Matcher Week
debashish_ghosal profile

The 6-Line Fix That Outperformed My Entire Matcher Week

#ai #llm #agents #testing
18
Comments 5
11 min read
Your "Encrypted" Reasoning Traces Aren't as Encrypted as You Think
uday_kocherla profile

Your "Encrypted" Reasoning Traces Aren't as Encrypted as You Think

#cybersecurity #llm #privacy #security
Comments 1
5 min read
Your LLM cannot compute a birth chart (and it won't tell you)
beachcombers profile

Your LLM cannot compute a birth chart (and it won't tell you)

#ai #llm #typescript #opensource
1
Comments
4 min read
What a Malicious Ollama Model Can Actually Do to Your Host, and How to Sandbox /api/pull
john_182319291 profile
John

What a Malicious Ollama Model Can Actually Do to Your Host, and How to Sandbox /api/pull

#ollama #security #llm #docker
Comments
13 min read
The Retrieval Pipeline Is Lying to You: How RAG Fails Before the LLM Sees Anything
hosseinhezami profile

The Retrieval Pipeline Is Lying to You: How RAG Fails Before the LLM Sees Anything

#ai #rag #llm #agents
6
Comments 3
13 min read
The $2,000 Inference Server: Standing Up Local AI on Ten-Year-Old Hardware
devbrewery profile

The $2,000 Inference Server: Standing Up Local AI on Ten-Year-Old Hardware

#ai #selfhosted #llm #homelab
1
Comments 4
5 min read
We're launching our LLM gateway with observability, evaluators and git-like prompt management.
petkovski profile

We're launching our LLM gateway with observability, evaluators and git-like prompt management.

#showdev #ai #llm #apigateway
2
Comments
1 min read
Changing the AI engine moved 3 of 10 results. Changing the question moved 10 of 10.
lana_connexion profile

Changing the AI engine moved 3 of 10 results. Changing the question moved 10 of 10.

#ai #llm #opensource #datascience
Comments
7 min read
Qwen3 235B Tops the Agentic Benchmark - What That Test Actually Measures
basavaraj_sh_1ea7d95f0f2e profile

Qwen3 235B Tops the Agentic Benchmark - What That Test Actually Measures

#llm #agents #langgraph #qwen
Comments
2 min read
Buyer context moved 6 of the top 10 results on one market. I ran it again on an unrelated market and it moved 4.
lana_connexion profile

Buyer context moved 6 of the top 10 results on one market. I ran it again on an unrelated market and it moved 4.

#ai #llm #datascience #machinelearning
Comments
7 min read
We built an AI security layer and kept AI out of the decision
christian_johannsen_a14e8 profile

We built an AI security layer and kept AI out of the decision

#ai #security #llm #compliance
Comments 1
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.