Topics
Results for “llms”
103 results
- The Case for Smart Software — DEV Community · Seen
- How Open-Source LLMs Differ: Comparing 130+ Model Architectures — DEV Community · Seen
- More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs — arXiv AI Papers · Seen
- Poetry 'resurrection' from LLMs — arXiv AI Papers · Seen
- Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs — arXiv AI Papers · Seen
- Understanding Positional Embeddings in Modern LLMs — Hacker News · Seen · 241 points
- How much does it cost to run a text game with LLMs — DEV Community · Seen
- Stop Asking LLMs to Do Math: Client-Side Functions in Flutter GenUI with bloc_signals — DEV Community · Seen
- Global Optimization for Combinatorial Geometry Problems Revisited in Era of LLMs — Hacker News · Seen · 3 points
- Jane Street – Our software engineering interviews are changing (a little) — Hacker News · Seen · 260 points
- I'm making LLMs work on small and old devices — Hacker News · Seen · 477 points
- LLMs and the Homogenization of Teaching — arXiv AI Papers · Seen
- What was your win this week? — DEV Community · Seen
- Research topics and write briefings with a personal agent — Agent Use Cases · Seen
- LLMs Play Zachtronics' TIS-100 — Hacker News · Seen · 91 points
- 37% on ARC-AGI-2 Kaggle Without LLMs — Hacker News · Seen · 3 points
- TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation — arXiv AI Papers · Seen
- TimeOmni-o1: Bidirectionally Coupling Time Series Foundation Models and LLMs for Multimodal Reasoning and Forecasting — arXiv AI Papers · Seen
- OSS projects banning AI-generated contributions — Hacker News · Seen · 51 points
- Show HN: TheoremSmith: Mass-Producing Hard Proof Problems to Train LLMs — Hacker News · Seen · 10 points
- AYO: A Safe and Privacy-Preserving Platform for Studying Children's Interaction with LLMs — arXiv AI Papers · Seen
- Veterans' Mental Health Crisis Severity Annotation: Do LLMs Agree More Than Human Experts? — arXiv AI Papers · Seen
- Counting Events, Not Seeing Them: Diagnosing and Repairing the Readout Failure in Video LLMs — arXiv AI Papers · Seen
- Rethinking Supervision Targets for Multimodal LLM Unlearning: Less Private Information, Reduced Distribution Shift — arXiv AI Papers · Seen
- Causal Discovery Bench: Can LLMs Autonomously Conduct Effective Experiments? — arXiv AI Papers · Seen
- Use it, or lose it 🧠 — DEV Community · Seen
- Writing as a Thinking Tool — Hacker News · Seen · 451 points
- The Wizard of Open Weights: Chris Alexiuk Makes AI Easy With Open Models — NVIDIA Blog · Seen
- I will not be using LLMs in my coding — Hacker News · Seen · 72 points
- Memorilla: Latent Semantic Memory for LLMs — Hacker News · Seen · 115 points
- SketchAgentBench – evaluate LLMs on 3D spatial reasoning — Hacker News · Seen · 9 points
- Can LLMs redesign themselves as they train? — Hacker News · Seen · 9 points
- Stop running everything through LLMs: How I fixed my research agent — Hacker News · Seen · 19 points
- The architecture of open-weight LLMs: MoE, hybrid layers, ternary weights — Hacker News · Seen · 16 points
- PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments — Hugging Face Papers · Seen · 38 points
- No Human Will Ever Write Code Better Than LLMs? Better at What? — DEV Community · Seen
- Qwen 3.8 27B on my laptop can interpret model weights, too — Hacker News · Seen · 713 points
- Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights — 2 sources · Seen · 2,935 points
- LLMs are not superhuman at reading and writing neural network weights — Hacker News · Seen · 145 points
- InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants — Hugging Face Papers · Seen · 46 points
- Mass attempted replication of old findings of LLMs with new models — Hacker News · Seen · 26 points
- dlouapre/nlp-before-llms — Hugging Face Spaces · Seen
- Bitnet.cpp: Efficient Edge Inference for Ternary LLMs — Hugging Face Papers · Seen · 18 points
- When Modernization Breaks Working Code: A Study of LLMs on Legacy PHP — Hacker News · Seen · 22 points
- Program — Lobsters · Seen · 11 points
- Ask HN: What hardware are you using to run local LLMs? — Hacker News · Seen · 42 points
- Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now? — arXiv AI Papers · Seen
- Sleep framework: A new way for LLMs to retain knowledge in continual learning — 2 sources · Seen · 271 points
- patchy631/ai-engineering-hub — GitHub Trending · Seen
- So I guess everyone uses LLMs to think now — 2 sources · Seen · 63 points
- Malware uses LLMs to rank victims by how much they're worth — Hacker News · Seen · 253 points
- Bouba Beats Kiki, and Other Regularities in the Subjective Preferences of LLMs — arXiv AI Papers · Seen
- From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs — arXiv AI Papers · Seen
- Can we trust LLMs to judge whether a research idea is novel? — Hugging Face Blog · Seen
- FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading — arXiv AI Papers · Seen
- Let the Gate Decide: Per-Lookup Precision for Quantized Conditional Memory in LLMs — arXiv AI Papers · Seen
- Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks — arXiv AI Papers · Seen
- Ask HN: What do you believe or not believe about AI? — Hacker News · Seen · 5 points
- Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs — arXiv AI Papers · Seen
- Free Lunch for LLMs Confidence: The RL Critic Already Knows — arXiv AI Papers · Seen