HackerTrans
TopNewTrendsCommentsPastAskShowJobs

codelion

no profile record

Submissions

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

lambdasec.github.io
2 points·by codelion·9 दिन पहले·0 comments

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

mlx-optiq.com
2 points·by codelion·27 दिन पहले·0 comments

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

mlx-optiq.com
3 points·by codelion·पिछला माह·0 comments

Zero-Dependency Programming

conjure.pages.dev
2 points·by codelion·3 माह पहले·0 comments

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

huggingface.co
2 points·by codelion·4 माह पहले·0 comments

From HashHop to Memory-Augmented Language Models

huggingface.co
2 points·by codelion·5 माह पहले·0 comments

The Optimal Architecture for Small Language Models

huggingface.co
1 points·by codelion·7 माह पहले·0 comments

Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement

huggingface.co
3 points·by codelion·7 माह पहले·0 comments

OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution

algorithmicsuperintelligence.ai
53 points·by codelion·7 माह पहले·9 comments

Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement

huggingface.co
1 points·by codelion·7 माह पहले·0 comments

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

huggingface.co
6 points·by codelion·8 माह पहले·0 comments

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

huggingface.co
3 points·by codelion·8 माह पहले·0 comments

comments

codelion
·26 दिन पहले·discuss
Using qwen3.6 27b locally with Claude code, it works well for simple coding tasks
codelion
·27 दिन पहले·discuss
[flagged]
codelion
·2 माह पहले·discuss
You can consider using Frame for the SAST part - https://github.com/lambdasec/frame
codelion
·3 माह पहले·discuss
How does it compare to some of the newer mlx inference engines like optiq that support turboquantization - https://mlx-optiq.pages.dev/
codelion
·4 माह पहले·discuss
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
·8 माह पहले·discuss
When mammals hunt other mammals strange things can happen.
codelion
·10 माह पहले·discuss
Whom to believe? Devin or Claude? - https://www.anthropic.com/engineering/multi-agent-research-s...
codelion
·पिछला वर्ष·discuss
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.