Hacker Newsnew | past | comments | ask | show | jobs | submit | codelion's submissionslogin
1.Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon (mlx-optiq.com)
2 points by codelion 1 hour ago | past | discuss
2.A 1B humanizer that matches human writing on an AI detector (mlx-optiq.com)
3 points by codelion 13 days ago | past | discuss
3.Zero-Dependency Programming (conjure.pages.dev)
2 points by codelion 76 days ago | past
4.Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens (huggingface.co)
2 points by codelion 3 months ago | past
5.From HashHop to Memory-Augmented Language Models (huggingface.co)
2 points by codelion 4 months ago | past
6.The Optimal Architecture for Small Language Models (huggingface.co)
1 point by codelion 5 months ago | past
7.Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement (huggingface.co)
3 points by codelion 6 months ago | past
8.OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution (algorithmicsuperintelligence.ai)
53 points by codelion 6 months ago | past | 9 comments
9.Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement (huggingface.co)
1 point by codelion 6 months ago | past
10.The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)
6 points by codelion 7 months ago | past
11.The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)
3 points by codelion 7 months ago | past
12.Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training (huggingface.co)
2 points by codelion 10 months ago | past | 1 comment
13.Internal Coherence Maximization(ICM): Label-Free Unsupervised Training Framework (github.com/codelion)
1 point by codelion 10 months ago | past
14.Unsupervised Model Improvement via Internal Coherence Maximization (huggingface.co)
1 point by codelion 10 months ago | past
15.Show HN: PTS Library – Analyze LLM reasoning through "thought anchors"
2 points by codelion 10 months ago | past
16.Automated Discovery of High-Performance GPU Kernels with OpenEvolve (huggingface.co)
4 points by codelion 11 months ago | past
17.Adaptive Classifier: Dynamic Text Classification with Continuous Learning (huggingface.co)
1 point by codelion 11 months ago | past
18.Show HN: DeepThink Plugin – Bring Gemini 2.5's parallel reasoning to open models
4 points by codelion 12 months ago | past
19.Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques (arxiv.org)
1 point by codelion 12 months ago | past
20.Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience
48 points by codelion on June 2, 2025 | past | 13 comments
21.Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning
397 points by codelion on May 28, 2025 | past | 68 comments
22.Show HN: OpenEvolve – open-source implementation of DeepMind's AlphaEvolve
8 points by codelion on May 20, 2025 | past | 3 comments
23.Pivotal Token Search (PTS): Identify critical decision points in LLM generations (github.com/codelion)
1 point by codelion on May 17, 2025 | past
24.Show HN: An adaptive classifier that detects hallucinations in LLM/RAG outputs (github.com/codelion)
1 point by codelion on March 7, 2025 | past | 1 comment
25.Show HN: OptiLLMBench – Test how inference optimization tricks scale up LLMs
2 points by codelion on Feb 17, 2025 | past
26.Adaptive Classification for Automatic LLM Temperature Optimization
1 point by codelion on Feb 3, 2025 | past
27.Show HN: A classifier that learns new categories without retraining from scratch
4 points by codelion on Feb 1, 2025 | past | 1 comment
28.Adaptive Classifier: Dynamic Text Classification with Continuous Learning (github.com/codelion)
2 points by codelion on Jan 24, 2025 | past
29.Show HN: Adaptive-classifier – text classification with continuous learning
5 points by codelion on Jan 21, 2025 | past | 1 comment
30.Entropy Decoding in Optillm and Early Results on GSM8k
1 point by codelion on Oct 20, 2024 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: