| | The Day Claude Brought a 110 Staff Company to a Standstill (gopubby.com) |
| 2 points by swolpers 36 days ago | past |
|
| | Once I Understood Where AI Is Heading, I Stopped Being Anxious About It (gopubby.com) |
| 2 points by swolpers 38 days ago | past | 1 comment |
|
| | TTS engines: WebSocket vs. sync is 5.5x, INT8 slower than fp16 on M4 (gopubby.com) |
| 2 points by KirMoisha 51 days ago | past |
|
| | Testing Nvidia's FP4: Running 70B LLMs on a Single RTX 5090 with Real Benchmarks (gopubby.com) |
| 2 points by Aedelon 87 days ago | past |
|
| | AI Skills Engineering Guide (gopubby.com) |
| 1 point by jdhwilkins 3 months ago | past |
|
| | AI Broke ARC-AGI-2 at 84.6% – But the Key Trick Is from 1972 (gopubby.com) |
| 1 point by Aedelon 3 months ago | past |
|
| | Pure LLMs Score 0% on ARC-AGI-2. Why the Third Wave of AI Looks Like the First (gopubby.com) |
| 1 point by Aedelon 3 months ago | past |
|
| | RWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0 (gopubby.com) |
| 2 points by Aedelon 3 months ago | past | 3 comments |
|
| | Reasoning Models Fabricate 75% of Their Explanations (ArXiv:2505.05410) (gopubby.com) |
| 4 points by Aedelon 3 months ago | past |
|
| | The Traceability Gap Blocking Real AI in Delivery Tools (gopubby.com) |
| 1 point by oddish-tv 6 months ago | past | 1 comment |
|
| | Creating a Knowledge Graph for ICD Codes Using LLMs (gopubby.com) |
| 3 points by teleforce 9 months ago | past |
|
| | We'll Soon Mod Our TV Shows Like We Mod Our Video Games (gopubby.com) |
| 1 point by rolph 9 months ago | past | 1 comment |
|
| | How Do I Evaluate Chunking Strategies for Rags (gopubby.com) |
| 1 point by thuwarakesh on May 29, 2025 | past |
|
| | My 7 Step Strategy to Fix Rags (gopubby.com) |
| 3 points by thuwarakesh on May 6, 2025 | past | 1 comment |
|
| | NumPy Alternative is built for GPUs and is 25X faster (gopubby.com) |
| 2 points by thuwarakesh on April 14, 2025 | past | 1 comment |
|
| | A Timeline of Significant Discoveries That Led to Better AI Reasoning (gopubby.com) |
| 2 points by thuwarakesh on March 22, 2025 | past |
|
| | Advanced Prompt Caching Techniques to Build Faster and Cheaper AI (gopubby.com) |
| 1 point by thuwarakesh on March 17, 2025 | past |
|
| | One of These Will Be Your Favorite Chunking Technique for Rags (gopubby.com) |
| 2 points by thuwarakesh on March 13, 2025 | past |
|
| | Prompt Engineering (For Everyday Tasks) Doesn't Have to Be So Complicated (gopubby.com) |
| 1 point by thuwarakesh on March 13, 2025 | past |
|
| | Should You Hire Developers Who Don't Use AI? (gopubby.com) |
| 4 points by bamboriz on March 3, 2025 | past | 2 comments |
|
| | What 2024 Taught Me About AI: Progress, Challenges, and Ethical Imperatives (gopubby.com) |
| 1 point by Kizert on Jan 19, 2025 | past |
|
| | Artificial Intelligence Needs a Brain Transplant to Avoid Imminent Collapse (gopubby.com) |
| 2 points by Willingham on Jan 7, 2025 | past |
|
| | LLM, Hybrid Search and Job Recommendation (gopubby.com) |
| 2 points by _spaceatom on July 29, 2024 | past |
|
| | AI Generated Art and Music (gopubby.com) |
| 2 points by qiakai on July 5, 2024 | past |
|
| | Multi-Head RAG: Optimizing Complex Query Retrieval (gopubby.com) |
| 2 points by qiakai on June 21, 2024 | past |
|
| | [flagged] Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU (gopubby.com) |
| 57 points by qiakai on June 21, 2024 | past | 29 comments |
|
| | US Proposal: Ban on Exporting Open Source ChatGPT Models (gopubby.com) |
| 2 points by dlimeng on May 12, 2024 | past |
|
| | OpenAI Live Update on May 13: ChatGPT and GPT-4 Surprises? (gopubby.com) |
| 2 points by dlimeng on May 11, 2024 | past |
|
| | ElevenLabs Challenges Suno and Udio AI Musicians Beware (gopubby.com) |
| 3 points by dlimeng on May 10, 2024 | past |
|
| | Building an AI Algorithm Based on a Neural Network to Classify Fish Species (gopubby.com) |
| 4 points by m-ahmed on Jan 19, 2024 | past |
|
|
| More |
