DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Hidden Code: Why Your Tech Stack Is a Philosophical Manifesto!!!

The Hidden Code: Why Your Tech Stack Is a Philosophical Manifesto!!!

1
Comments
5 min read
When a reasoning model's <think> block leaks a JSON draft into your parser

When a reasoning model's <think> block leaks a JSON draft into your parser

Comments
3 min read
Is everything on here AI generated?

Is everything on here AI generated?

Comments 1
1 min read
We serve a sovereign inference tier from four Intel Arc Pro B60 — here's what it actually does (and doesn't)

We serve a sovereign inference tier from four Intel Arc Pro B60 — here's what it actually does (and doesn't)

1
Comments 3
5 min read
Our voice agent costs 2.5¢ a minute. Here's the whole bill.

Our voice agent costs 2.5¢ a minute. Here's the whole bill.

Comments
2 min read
Treat Voice-Companion Memory as a Consent Ledger, Not Prompt History

Treat Voice-Companion Memory as a Consent Ledger, Not Prompt History

Comments
11 min read
Prompts Lie. Permissions Don't.

Prompts Lie. Permissions Don't.

Comments 1
3 min read
Is Claude Actually Better If You Can't Rely on It When It Matters?

Is Claude Actually Better If You Can't Rely on It When It Matters?

Comments 2
4 min read
I asked an LLM to cut 14 texts by 20–30%. Median: only 7%

I asked an LLM to cut 14 texts by 20–30%. Median: only 7%

Comments
5 min read
I benchmarked Cloudflare's new open decision model against the hosted API it's trying to replace

I benchmarked Cloudflare's new open decision model against the hosted API it's trying to replace

1
Comments 1
4 min read
How LLM Evaluation Produces Comparable Numbers: Inside the LFORLA Reverse Engineering Benchmark

How LLM Evaluation Produces Comparable Numbers: Inside the LFORLA Reverse Engineering Benchmark

2
Comments 1
4 min read
Determinism Injection

Determinism Injection

Comments
3 min read
Estimate your AI feature's model bill before you build it

Estimate your AI feature's model bill before you build it

Comments
2 min read
Quando o eval reprova o eval: avaliando um agente Google ADK sem tools

Quando o eval reprova o eval: avaliando um agente Google ADK sem tools

Comments
12 min read
I Let an LLM Rewrite Its Own Prompt. The Real Win Was the Gate That Rejected It.

I Let an LLM Rewrite Its Own Prompt. The Real Win Was the Gate That Rejected It.

11
Comments 1
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.