1021
Gemini 2.5 Pro reasons about task feasibility
... in which a surprisingly reflective AI tells me no (for good reasons) ...
New
The latest blog posts to take off on Hacker News. 1,227 posts.
1022
4o Image Generation
This 2025 launch introduced native image generation in GPT‑4o, including stronger text rendering and instruction following. Explore ChatGPT Images 2.5.
1023
Gemini 2.5
Gemini 2.5 is our most intelligent AI model, now with thinking.
1024
Noise cancellation improves turn-taking for AI Voice Agents
Turn-Taking is a big challenge AI Voice Agents are rapidly evolving, powering critical use-cases such as customer support automation, virtual assistants, gaming, and remote collaboration platforms. For these voice-driven interactions to feel natural and practical, the underlying audio pipeline must be resilient to…
1025
Arc-AGI-2 and ARC Prize 2025
Measuring the next level of intelligence with ARC-AGI-2 and ARC Prize 2025
1026
Qwen2.5-VL-32B: Smarter and Lighter
QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD Introduction At the end of January this year, we launched the Qwen2.5-VL series of models, which received widespread attention and positive feedback from the community. Building on the Qwen2.5-VL series, we continued to optimize the model using reinforcement learning…
1027
Project Aardvark: reimagining AI weather prediction
From the Global South to the Arctic, can machine learning-enabled weather prediction better protect communities and economies?
1028
Aiter: AI Tensor Engine for ROCm
We introduce AMD's AI Tensor Engine for ROCm (AITER), our centralized high performance AI operators repository, designed to significantly accelerate AI workloads on AMD GPUs
1029
Bitter Lesson is about AI agents
The Race for AI Progress In 2019, Richard Sutton, wrote his groundbreaking essay titled ‘The Bitter Lesson’. Simply put, the essay concludes that systems which get better with higher compute beat the systems that do not. Or specifically in AI: raw computing power consistently wins over intricate human-designed…
1030
A (Long) Peek into Reinforcement Learning
[Updated on 2020-09-03: Updated the algorithm of SARSA and Q-learning so that the difference is more pronounced. [Updated on 2021-09-19: Thanks to 爱吃猫的鱼, we have this post in Chinese].
1031
Improving recommendation systems and search in the age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
1032
Not all AI-assisted programming is vibe coding (but vibe coding rocks)
Vibe coding is having a moment. The term was coined by Andrej Karpathy just a few weeks ago (on February 6th) and has since been featured in the New York …
1033
“Vibe Coding” vs. Reality
Reviewing the capabilities and limitations of LLM agents in software development and their impact on skilled and less skilled developers.
1034
Most AI value will come from broad automation, not from R & D
AI's biggest impact will come from broad labor automation—not R&D—driving economic growth through scale, not scientific breakthroughs.
1035
Map Features in OpenStreetMap with Computer Vision
Mozilla.ai developed and released the OpenStreetMap AI Helper Blueprint. If you love maps and are interested in training your own computer vision model, you’ll enjoy diving into this Blueprint.
1036
PyTorch Internals: Ezyang's Blog
This post is a long form essay version of a talk about PyTorch internals, that I gave at the PyTorch NYC meetup on May 14, 2019.
1037
1038
Claude can now search the web
Claude can now search the internet to provide up-to-date, cited responses on all plans worldwide. Get real-time insights for research, market analysis, and more.
1039
Block AI Scrapers with Anubis proof-of-work
I got tired with all the AI scrapers that were bullying my git server, so I made a tool to stop them for good.
1040
How I accepted myself into Canada's largest AI hackathon
i <3 firebase
1041
Orpheus-3B – Emotive TTS by Canopy Labs
Canopy Labs is developing digital humans that are indistinguishable from real ones.
1042
LLM Agents Are Simply Graph – Tutorial for Dummies
Ever wondered how AI agents actually work behind the scenes?
1043
AI Blindspots – Blindspots in LLMs I've noticed while AI coding
Blindspots in LLMs I’ve noticed while AI coding. Sonnet family emphasis. Maybe I will eventually suggest Cursor rules for these problems.
1044
Fine-tune Google's Gemma 3
Gemma 3, Google's new multimodal models. Fine-tune & Run them with Unsloth! Gemma 3 comes in 1B, 4B, 12B and 27B sizes.
1045
Trapping misbehaving bots in an AI Labyrinth
How Cloudflare uses generative AI to slow down, confuse, and waste the resources of AI Crawlers and other bots that don’t respect “no crawl” directives.
1046
Hacking Your Own AI Coding Assistant with Claude Pro and MCP
Reverse Engineering Reality
1047
Diagrams AI can, and cannot, generate
An exploration of how well AI generates system architecture diagrams
1048
The model is the product
Old data, new models
1049
How Cursor (AI IDE) Works
Turning LLMs into coding experts and how to take advantage of them.
1050
AI Is Making Developers Dumb
LLMs are making software engineers dumber.