codelion

codelion

vor 26 Tagendiscuss

Using qwen3.6 27b locally with Claude code, it works well for simple coding tasks

codelion

vor 27 Tagendiscuss

[flagged]

codelion

vor 2 Monatendiscuss

You can consider using Frame for the SAST part - https://github.com/lambdasec/frame

codelion

vor 3 Monatendiscuss

How does it compare to some of the newer mlx inference engines like optiq that support turboquantization - https://mlx-optiq.pages.dev/

codelion

vor 4 Monatendiscuss

the key issue is the interpretation of "consent" when continued use is the only option. aree users truly consenting, or are they simply left with no alternative?

codelion

vor 8 Monatendiscuss

When mammals hunt other mammals strange things can happen.

codelion

vor 10 Monatendiscuss

Whom to believe? Devin or Claude? - https://www.anthropic.com/engineering/multi-agent-research-s...

codelion

letztes Jahrdiscuss

Really interesting benchmark, thanks for sharing! It's good to see some real-world comparisons. The hallucinations issue is definitely a key concern with LLM-based OCR, and it's important to quantify that risk. Looking forward to seeing the full benchmark results.

Submissions

Frame: Grounding LLM Vulnerability Detection with a Sound Separation-Logic Core

Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon

A 1B humanizer that matches human writing on an AI detector

Zero-Dependency Programming

Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens

From HashHop to Memory-Augmented Language Models

The Optimal Architecture for Small Language Models

Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement

OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution

Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement

The 1B Token Challenge: Finding the Perfect Pre-Training Mix

The 1B Token Challenge: Finding the Perfect Pre-Training Mix

comments