DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
What Might the Next Generation of AI Look Like?

What Might the Next Generation of AI Look Like?

9
Comments 2
13 min read
Taming Clinical Hallucinations: How We Mapped Colloquial Patient Slang to 350,000+ SNOMED CT Concepts Using AWS Bedrock & Vector Disambiguation

Taming Clinical Hallucinations: How We Mapped Colloquial Patient Slang to 350,000+ SNOMED CT Concepts Using AWS Bedrock & Vector Disambiguation

Comments
8 min read
I put my multi-model dispatch queue and its monthly spend beside the Claude Code chat. 1,330 lines, 37 ms.

I put my multi-model dispatch queue and its monthly spend beside the Claude Code chat. 1,330 lines, 37 ms.

1
Comments
5 min read
A Correct Outcome Does Not Necessarily Mean the Process Was Acceptable

A Correct Outcome Does Not Necessarily Mean the Process Was Acceptable

Comments
5 min read
Your use case is not in the benchmarks

Your use case is not in the benchmarks

Comments
11 min read
Agent skills after the install button: 6 reads on loading, gain checks, conflicts, state machines and trust

Agent skills after the install button: 6 reads on loading, gain checks, conflicts, state machines and trust

Comments
4 min read
Gemini 4 Neon: The Balance Point Between Carbon and Hydrogen — Benchmarks, API Pricing, and Orchestrator Workflows

Gemini 4 Neon: The Balance Point Between Carbon and Hydrogen — Benchmarks, API Pricing, and Orchestrator Workflows

Comments
10 min read
Same AI model, five weeks later: the cheapest provider had changed

Same AI model, five weeks later: the cheapest provider had changed

Comments
7 min read
Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning

Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning

Comments
2 min read
GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing

GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing

Comments
12 min read
One sentence stopped my AI agents inventing data. Bad data that looked normal still fooled them.

One sentence stopped my AI agents inventing data. Bad data that looked normal still fooled them.

Comments
5 min read
Context is the job

Context is the job

Comments
7 min read
I Autoscaled My LLM on Queue Depth. It Scaled Down Under Full Load.

I Autoscaled My LLM on Queue Depth. It Scaled Down Under Full Load.

4
Comments 3
10 min read
Generating YouTube titles and thumbnail ideas from a transcript without putting words in the creator's mouth

Generating YouTube titles and thumbnail ideas from a transcript without putting words in the creator's mouth

Comments
2 min read
Showing my work: the four artifacts behind an AI judge for generated courses (part 1)

Showing my work: the four artifacts behind an AI judge for generated courses (part 1)

1
Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.