DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
DiffusionGemma: The Developer Guide

DiffusionGemma: The Developer Guide

19
Comments 2
5 min read
Prose in the Control Plane: Why AI Agent Frameworks Are Not Engineering (Yet)

Prose in the Control Plane: Why AI Agent Frameworks Are Not Engineering (Yet)

Comments
7 min read
The Agent Faked a Test Log, Then Believed It. Self-Editing Harnesses Have a Provenance Problem.

Agents reinventing operations engineering

The Agent Faked a Test Log, Then Believed It. Self-Editing Harnesses Have a Provenance Problem.

24
Comments 39
12 min read
Our few-shot examples came from the eval set. The 0.94 was fiction.

Our few-shot examples came from the eval set. The 0.94 was fiction.

6
Comments 10
13 min read
Blocking Prompt Injection Before It Reaches Your LLM

Blocking Prompt Injection Before It Reaches Your LLM

Comments 1
5 min read
Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip

Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip

Comments
7 min read
Using the System Prompt / Preferences Field

Using the System Prompt / Preferences Field

Comments
4 min read
GLM 5.2 Just Dropped: What Zhipu's New Open-Weights Flagship Means for Developers

GLM 5.2 Just Dropped: What Zhipu's New Open-Weights Flagship Means for Developers

Comments
2 min read
Superpowers vs Agent Skills vs Pocock: Three Philosophies of AI Coding Workflows

Superpowers vs Agent Skills vs Pocock: Three Philosophies of AI Coding Workflows

4
Comments
8 min read
Frontier Bakeoff: We Benchmarked Fable 5 Hours Before the Shutdown

Frontier Bakeoff: We Benchmarked Fable 5 Hours Before the Shutdown

Comments
6 min read
AI Agent Autonomy Levels: From Logged to Locked Down

AI Agent Autonomy Levels: From Logged to Locked Down

6
Comments 4
8 min read
I almost burned ₹4,000 on Claude API overnight — so I built llm-cost-guard

I almost burned ₹4,000 on Claude API overnight — so I built llm-cost-guard

Comments
3 min read
Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions

Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions

6
Comments
10 min read
Local-First Agentsview, Raspberry Pi Agent Deployment, Unified AI Suite

Local-First Agentsview, Raspberry Pi Agent Deployment, Unified AI Suite

Comments
3 min read
Building an AI Agent That Knows When Not to Guess (Qwen + MCP)

Uncertainty as a first-class output

Building an AI Agent That Knows When Not to Guess (Qwen + MCP)

29
Comments 30
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.