DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I got tired of Django being left behind in UI, so I built a shadcn/ui equivalent.

I got tired of Django being left behind in UI, so I built a shadcn/ui equivalent.

Comments
2 min read
Can Multi-Model Discussion Actually Solve AI Hallucination? A Reflection from an MVP Practitioner

Can Multi-Model Discussion Actually Solve AI Hallucination? A Reflection from an MVP Practitioner

Comments
3 min read
Built a proxy, so my AI coding sessions stop forgetting everything after 20 turns

Built a proxy, so my AI coding sessions stop forgetting everything after 20 turns

Comments
2 min read
Point any app at a local LLM on your Mac (OpenAI-compatible endpoints)

Point any app at a local LLM on your Mac (OpenAI-compatible endpoints)

Comments
4 min read
AI Agents That Speak SQL: Text-to-SQL with Hugging Face smolagents

AI Agents That Speak SQL: Text-to-SQL with Hugging Face smolagents

4
Comments
4 min read
AI Fabricates Maxims: Caught Twice by Human Review in One Day

AI Fabricates Maxims: Caught Twice by Human Review in One Day

Comments
6 min read
Inference Optimization for the Rest of Us — KV Cache, Quantization, and Latency Tradeoffs

Inference Optimization for the Rest of Us — KV Cache, Quantization, and Latency Tradeoffs

Comments
5 min read
From Stateless Prompts to Persistent Intelligence: Why I Started Building Hystersis

From Stateless Prompts to Persistent Intelligence: Why I Started Building Hystersis

Comments
4 min read
4 New Claude Models Just Dropped: Sonnet 5, Fable 5, Opus 4.6 Pricing Compared

4 New Claude Models Just Dropped: Sonnet 5, Fable 5, Opus 4.6 Pricing Compared

Comments
8 min read
26 AI Models Compared: A 2026 Cost Guide (GPT-4o vs Claude vs DeepSeek vs Local)

26 AI Models Compared: A 2026 Cost Guide (GPT-4o vs Claude vs DeepSeek vs Local)

Comments
8 min read
Reliable AI Agent Control Flow: Keep the State Machine Out of the Prompt

Reliable AI Agent Control Flow: Keep the State Machine Out of the Prompt

Comments
8 min read
DocWire SDK 2026.07.07 — llama.cpp backend, IBM Granite by default, and a codebase-wide rename

DocWire SDK 2026.07.07 — llama.cpp backend, IBM Granite by default, and a codebase-wide rename

Comments
3 min read
The smartest model lost — and it just redrew the 2026 AI race

The smartest model lost — and it just redrew the 2026 AI race

Comments
4 min read
Grok 4.5: what the numbers say beyond xAI's announcement

Grok 4.5: what the numbers say beyond xAI's announcement

Comments
3 min read
Beyond One-Shot: The Recursive Reflection Framework for Polished AI Outputs

Beyond One-Shot: The Recursive Reflection Framework for Polished AI Outputs

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