DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit

Why Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit

Comments 2
7 min read
I built a CLI that estimates LLM API cost before you send the request

I built a CLI that estimates LLM API cost before you send the request

Comments
1 min read
Building with Local LLMs: An Engineer's Approach to AI-Assisted Development

Building with Local LLMs: An Engineer's Approach to AI-Assisted Development

1
Comments
5 min read
Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content

Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content

Comments
3 min read
I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz

I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz

Comments
4 min read
Measured: the last Sonnet update started wrapping raw JSON in a markdown fence

Measured: the last Sonnet update started wrapping raw JSON in a markdown fence

Comments
4 min read
Why We Treat Prompts Like Infrastructure, Not Conversations

Why We Treat Prompts Like Infrastructure, Not Conversations

Comments
3 min read
Architecting lean LLM caching: how to drop a 20M-row table without losing your AI memory

Architecting lean LLM caching: how to drop a 20M-row table without losing your AI memory

2
Comments 2
4 min read
Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't

Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't

2
Comments
20 min read
0.2.0: I shipped the coverage my own page had already promised

0.2.0: I shipped the coverage my own page had already promised

Comments
7 min read
Kimi K3: The Frontier Just Went Open

Kimi K3: The Frontier Just Went Open

Comments
7 min read
The four parts of a prompt you can actually trust

The four parts of a prompt you can actually trust

Comments
1 min read
Session Pending and Memory Layers in Solon Agents: Pause Runs, Isolate History, Resume Work

Session Pending and Memory Layers in Solon Agents: Pause Runs, Isolate History, Resume Work

Comments
5 min read
The Server Is Fine. The Model Still Can't Use It.

The Server Is Fine. The Model Still Can't Use It.

1
Comments 2
4 min read
How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents

How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents

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