931
Instant 1.0, a backend for AI-coded apps
Instant 1.0 is out! This essay shows a bunch of demos, to explain why we think Instant is the best backend for AI-coded apps. We also cover the architecture that makes all of it work.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 1,521 posts.
932
Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions
<p>As a fun personal project, I have been working on a chatbot for answering general questions about my household on anything from maintenance questions to doctor’s appointments. </p> <p> The general idea is that the chatbot will get its household knowledge through RAG from querying a vector database, but for better…
933
Anthropic's Safety Superpower
Anthropic’s belief in its own commitment to safety gives the company license to aggressively favor its business and even challenge the U.S. government.
934
935
Research-Driven Agents: When an agent reads before it codes
Coding agents working from code alone generate shallow hypotheses. Adding a research phase — arxiv papers, competing forks, other backends — produced 5 kernel fusions that made llama.cpp CPU inference 15% faster.
936
Language models for text classification: From bag-of-words to Jev
A Visual Guide to RNNs, CNNs, Transformers, and Calibration, with Hands-On Experiments on Accuracy and Efficiency
937
OpenAI, the Partition Principle, and Mathematics
By the time I got out of bed yesterday, I had three people ask me if I'd seen the OpenAI announcement that the Partition Principle does not (...)
938
An AI Vibe Coding Horror Story
A medical professional built a patient management app using AI, exposed all patient data unprotected to the internet, and sent voice recordings to AI services without consent. Likely violating Swiss nDSG and other laws.
939
940
Please stop flooding our projects with AI slop to furnish your CV
Successful contributions to open source projects are a kind of currency. GitHub in particular encourages this in a number of ways: by showing avatars of contributors on repository pages, by showing your contributions to your followers via the activity feed and by signalling contributions per day on the activity graph…
941
Here be monsters: What do you still need to know when agents do the work?
AI agents write code faster than anyone can read it. What engineers still need: fundamentals, breadth, and the willingness to dive in when it breaks.
942
LLMs Are Complicated Now
Back in 2022 and 2023 there were two big branches of machine learning happening at Meta1. The LLM work that led to Llama was a clean, smooth stack of repeated Transformer modules; the recommendatio…
943
FLUX 3 Image Klein
Frontier image quality with the customization and speed of open weights: 5.6B parameters, first in text-to-image, multi-reference generation and editing.
944
Qwen-Robot Suite: A Foundation Model Suite for Physical World Intelligence
Qwen offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
945
Where does next-token prediction leave us?
Your favourite ROP gadget
946
Research acceleration: The view inside OpenAI
Inside OpenAI, coding agents are reshaping AI research. Explore early data on agent usage, experiment velocity, task complexity, and research acceleration.
947
Anti-AI fonts are useless and harmful
Trying to obfuscate the web is a bad, pointless idea
948
Furiosa: 3.5x efficiency over H100s
Meet the RNGD Server, delivering scalable, energy-efficient AI inference at data center scale with FuriosaAI’s Renegade accelerator platform.
949
Vāgdhenu: A Sanskrit Chanting TTS System
A vṛtta (meter) aware śloka-to-chant system for Sanskrit. Try the live demo, hear sample chants, read the paper.
950
The Agentic AI Handbook: Production-Ready Patterns
A comprehensive guide to 113 production-informed patterns for building reliable AI agents.
951
What mathematicians should know about the Lean Theorem Prover: reliability & AI
[This is a guest post by Thomas Hales. This blog post was initially written in a different file format and converted using AI. — T.] Mathematicians have been weighing in on what they value ab…
952
Eurostar AI vulnerability: When a chatbot goes off the rails
TL;DR Introduction I first encountered the chatbot as a normal Eurostar customer while planning a trip. When it opened, it clearly told me that “the answers in this chatbot are generated by AI”, which is good disclosure but immediately raised my curiosity about how it worked and what its limits were. Eurostar…
953
Data is the only moat
How different adoption models drive better applications
954
Waymo Premier
As we scale and bring our fully autonomous ride-hailing service to more people across the globe, we continue to refine the Waymo experience and deliver more for our riders. You spoke, and we listened to how we can offer an even more elevated experience for you, our top riders. Introducing: Waymo Premier.
955
A €0.01 bank transfer could compromise a banking AI agent
Blue41 helps regulated organizations monitor AI agent behavior, detect manipulation and misuse, and prove that sensitive workflows stay within safe boundaries.
956
Jellyfin LLM/"AI" Development Policy
The rise of LLMs as a useful development tool over the last year or so has been significant. The power and flexibility of tools like Claude Code and ChatGPT have given a lot of functionality both to experienced developers and new developers alike. But there are trade-offs.
957
MiniMax M2.5 released: 80.2% in SWE-bench Verified
MiniMax M2.5: Built for Real-World Productivity.
958
Shall we play a game? My AI nuclear simulation
My AI nuclear simulation is out now, and it's a WOPR.
959
Responding to the next frontier of critical cyber capabilities
OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.
960
My spicy take on vibe coding for PMs
I shared this internally at Meta in response to a deluge of clout-chasing posts celebrating PMs landing prod diffs. The response was positive and the message generalizes, so here we are on the open www. PMs shouldn’t waste time landing … Continue reading →