Forem

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Gemma-4-31B on v6e-4 TPU Benchmarks
Cover image for Gemma-4-31B on v6e-4 TPU Benchmarks

Gemma-4-31B on v6e-4 TPU Benchmarks

7
Comments
2 min read
I Built a 7-Agent Prompt Framework, Then Used It to Debug Its Own Output
Cover image for I Built a 7-Agent Prompt Framework, Then Used It to Debug Its Own Output

I Built a 7-Agent Prompt Framework, Then Used It to Debug Its Own Output

Comments
6 min read
When one translation isn't enough: building konid

When one translation isn't enough: building konid

Comments
2 min read
All Data and AI Weekly #238-20April2026
Cover image for All Data and AI Weekly #238-20April2026

All Data and AI Weekly #238-20April2026

5
Comments
11 min read
Opus 4.7 First Look: I Tested the Day-Old Model Against 3 Other Claudes on 10 Real Tasks
Cover image for Opus 4.7 First Look: I Tested the Day-Old Model Against 3 Other Claudes on 10 Real Tasks

Opus 4.7 First Look: I Tested the Day-Old Model Against 3 Other Claudes on 10 Real Tasks

Comments 1
5 min read
LLM routing per tier via OpenRouter — when one model doesn't fit all
Cover image for LLM routing per tier via OpenRouter — when one model doesn't fit all

LLM routing per tier via OpenRouter — when one model doesn't fit all

Comments
6 min read
Why AI Teams Are Standardizing on a Multi-Model Gateway

Why AI Teams Are Standardizing on a Multi-Model Gateway

1
Comments
2 min read
The 96.3% Is a Trap: What Hermes 4 405B Actually Changed

The 96.3% Is a Trap: What Hermes 4 405B Actually Changed

Comments
8 min read
Local Voice-Controlled AI Agent (Whisper + Ollama + Streamlit)

Local Voice-Controlled AI Agent (Whisper + Ollama + Streamlit)

Comments
2 min read
EcomRLVE-GYM: Bài toán thật của shopping agent là hoàn tất giao dịch, không chỉ nói hay

EcomRLVE-GYM: Bài toán thật của shopping agent là hoàn tất giao dịch, không chỉ nói hay

Comments
23 min read
I tried to hack my local AI agent with Prompt Injection. It laughed at me.
Cover image for I tried to hack my local AI agent with Prompt Injection. It laughed at me.

I tried to hack my local AI agent with Prompt Injection. It laughed at me.

Comments
4 min read
Why Your Production LLM Prompt Keeps Failing (And How to Diagnose It in 4 Steps)
Cover image for Why Your Production LLM Prompt Keeps Failing (And How to Diagnose It in 4 Steps)

Why Your Production LLM Prompt Keeps Failing (And How to Diagnose It in 4 Steps)

1
Comments 1
5 min read
Show HN: veez-pii-guard – anonymize PII before LLM calls, pure Go, offline, 0.019ms

Show HN: veez-pii-guard – anonymize PII before LLM calls, pure Go, offline, 0.019ms

Comments 2
1 min read
Introducing Portkey's Agent Gateway
Cover image for Introducing Portkey's Agent Gateway

Introducing Portkey's Agent Gateway

1
Comments
2 min read
I Tried Building GPT Without Training — Just Math. Here’s Where It Broke | Shivnath Tathe
Cover image for I Tried Building GPT Without Training — Just Math. Here’s Where It Broke | Shivnath Tathe

I Tried Building GPT Without Training — Just Math. Here’s Where It Broke | Shivnath Tathe

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