601
Which table format do LLMs understand best?
We benchmarked 11 data formats, including markdown tables, JSON, CSV, YAML, XML, and more, to see which LLMs understand best. We found surprising accuracy and token cost trade-offs.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 1,227 posts.
602
Minecraft with object impermanence
I generally am uninterested in generative AI that's too close to the real thing. But every once in a while there's a modern AI thing that's so glitchy and broken that it's strangely compelling. There's this generative AI knockoff of Minecraft that fails so hard
603
Our LLM-controlled office robot can't pass butter
Can LLMs control robots? We answer this by testing how good models are at passing the butter – or more generally, do delivery tasks in a household setting. State of the art models struggle, with the best model scoring 40% at Butter-Bench, compared to 95% for humans.
604
DeepSearcher: A local open-source Deep Research
In contrast to OpenAI’s Deep Research, this example ran locally, using only open-source models and tools like Milvus and LangChain.
605
AI is making us work more
How tools that were supposed to free us up to find meaning work have exacerbated the rat race.
606
MCP doesn't need tools, it needs code
Exploration into providing MCPs with the most powerful of all tools: code.
607
608
MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming
在 M2.1 中, 我们系统性提升了 Rust / Java / Golang / C++ / Kotlin / Objective-C / TypeScript / JavaScript 等语言的能力, 多语言任务整体表现达到业内领先水平, 覆盖从底层系统到应用层开发的完整链路。
609
Let's properly analyze an AI article for once
Recently the CEO of Github wrote a blog post called Developers reinvented . It was reposted with various clickbait headings like GitHub CEO...
610
Look, Another AI Browser
Yesterday, OpenAI announced Atlas, its AI browser. To the surprise of literally nobody, it’s Chromium with AI slapped on top. Perplexity also has a …
611
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.
612
FunctionGemma 270M Model
FunctionGemma is a specialized version of our Gemma 3 270M model fine-tuned for function calling.
613
A Gemma model helped discover a new potential cancer therapy pathway
We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models.
614
615
Vibe coding creates a bus factor of zero
"AI first" leaves humans nowhere. Learn about the Bus Factor and how the launch of ChatGPT has changed the landscape on knowledge sharing.
616
Qwen VLo: From “Understanding” the World to “Depicting” It
QWEN CHAT DISCORD Introduction The evolution of multimodal large models is continually pushing the boundaries of what we believe technology can achieve. From the initial QwenVL to the latest Qwen2.5 VL, we have made progress in enhancing the model’s ability to understand image content. Today, we are excited to…
617
Alexa+
Powered by generative AI, Alexa+ is your personal AI assistant that gets things done—she’s smarter, more conversational, more capable, and free with Prime.
618
The current state of LLM-driven development
I spent the past ~4 weeks trying out all the new and fancy AI tools for software development.
619
How we used GPT-4o for image detection with 350 similar illustrations
The Attic is a running catalog of Olup's side projects, sketches, and weekend rabbit holes.
620
The current state of the theory that GPL propagates to AI models
When GitHub Copilot was launched in 2021, the fact that its training data included a vast amount of Open Source code publicly available on GitHub attracted significant attention, sparking lively de…
621
“Vibe Coding” vs. Reality
Reviewing the capabilities and limitations of LLM agents in software development and their impact on skilled and less skilled developers.
622
New coding models and integrations
GLM-4.6 and Qwen3-coder-480B are available on Ollama’s cloud service with easy integrations to the tools you are familiar with. Qwen3-Coder-30B has been updated for faster, more reliable tool calling in Ollama’s new engine.
623
Problems the AI industry is not addressing adequately
As a supporter, I would love not to feel this way
624
625
LLMs pose an interesting problem for DSL designers
The most exciting part of Programming Languages (PL) research for me has always been in Programming Language Design.
626
Managing context on the Claude Developer Platform
New context editing and memory tools enable Claude agents to handle long-running tasks without hitting context limits.
627
Q-learning is not yet scalable
Over the past few years, we've seen that next-token prediction scales, denoising diffusion scales, contrastive learning scales, and so on, all the way to the point where we can train models with billions of parameters with a scalable objective that can eat up as much data as we can throw at it. Then, what about…
628
The Hater's Guide to the AI Bubble
Hey! Before we go any further — if you want to support my work, please sign up for the premium version of Where’s Your Ed At, it’s a $7-a-month (or $70-a-year) paid product where every week you get a premium newsletter, all while supporting my
629
Test-driven development with an LLM for fun and profit
Welcome to the very first post in a new blog! Here I will discuss software development, SRE work, and other fun stuff. Sometimes an idea is just too good to pass up. I hope this blog will motivate me to turn sparks and little pieces into general knowledge in writing the words down. The other day I was discussing Tabby…
630
Claude can sometimes prove it
We take pride in personally connecting with all interested partners, collaborators and potential clients. Please email us with a brief description of how you would like to be connected with Galois and we will do our best to respond within one business day.