31
Get an AI code review in 10 seconds
Personal Musings and Transcripts
New
The latest blog posts to take off on Hacker News. 1,227 posts.
32
Structured outputs create false confidence
Constrained decoding seems like the greatest thing since sliced bread, but it often forces models to prioritize output conformance over output quality.
33
Measuring AI Ability to Complete Long Tasks
We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been consistently exponentially increasing over the past 6 years, with a doubling time of around 7 months. Extrapolating this trend predicts that, in under a decade, we will see AI agents that can…
34
35
Skills Officially Comes to Codex
Give ChatGPT and Codex new capabilities and expertise
36
LLM Year in Review
2025 Year in Review of LLM paradigm changes
37
1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
Apple gave me access to this Mac Studio cluster to test RDMA over Thunderbolt, a new feature in macOS 26.2. The easiest way to test it is with Exo 1.0, an open source private AI clustering tool. RDMA lets the Macs all act like they have one giant pool of RAM, which speeds up things like massive AI models. The stack of…
38
AI vending machine was tricked into giving away everything
Anthropic installed an AI-powered vending machine in the WSJ office. The LLM, named Claudius, was responsible for autonomously purchasing inventory from wholesa
39
Two kinds of vibe coding
Back in 2009 I posted a simple Mandelbrot fractal viewer on the web: a single HTML file with inline Javascript. Just 329 lines of code, each pixel a tiny table cell. Click to zoom. Watch it iterate. That was about it!
40
T5Gemma 2: The next generation of encoder-decoder models
T5Gemma 2 is the next evolution of our encoder-decoder family based on Gemma 3.
41
FunctionGemma 270M Model
FunctionGemma is a specialized version of our Gemma 3 270M model fine-tuned for function calling.
42
GPT-5.2-Codex
GPT-5.2-Codex is OpenAI’s most advanced coding model, offering long-horizon reasoning, large-scale code transformations, and enhanced cybersecurity capabilities.
43
Skills for organizations, partners, the ecosystem
In October, we introduced skills—a way to teach Claude repeatable workflows tailored to how you work. Today we're making skills easier to deploy, discover, and build: organization-wide management for admins; a directory of partner-built skills from Notion, Canva, Figma, Atlassian, and others; and an open standard so…
44
Mistral OCR 3
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
45
AI helps ship faster but it produces 1.7× more bugs
We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.
46
Developers can now submit apps to ChatGPT
Developers can now submit apps for review and publication in ChatGPT, with approved apps appearing in a new in-product directory for easy discovery. Updated tools, guidelines, and the Apps SDK help developers build powerful chat-native experiences that bring real-world actions into ChatGPT.
47
AWS CEO says replacing junior devs with AI is 'one of the dumbest ideas'
AWS CEO Matt Garman pushes back on AI replacing junior developers and explains how AI should be used in the workplace.
48
The State of AI Coding Report 2025
Read the full Q2 2026 research report, explore the chart data, and download the PDF for free.
49
Gemini 3 Flash: Frontier intelligence built for speed
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
50
Coursera to combine with Udemy
Highly Complementary Capabilities Will Create a Leading Technology Platform, Redefining Skills Discovery, Development, and Mastery for Learners and Organizations at Scale Unites Udemy’s Dynamic AI-Powered Skills Development Marketplace with World-Class University and Industry Brands Under the Coursera Ecosystem…
51
AI's real superpower: consuming, not creating
Everyone's using AI wrong. Its superpower isn't writing for you. It's reading everything you've ever written and finding patterns you missed.
52
I ported JustHTML from Python to JavaScript with Codex CLI and GPT-5.2 in hours
I wrote about JustHTML yesterday—Emil Stenström’s project to build a new standards compliant HTML5 parser in pure Python code using coding agents running against the comprehensive html5lib-tests testing library. Last …
53
No AI* Here – A Response to Mozilla's Next Chapter
Mozilla's pivot to AI first browsing raises fundamental questions about what a browser should be.
54
AI will make formal verification go mainstream
Much has been said about the effects that AI will have on software development, but there is an angle I haven’t seen talked about: I believe that AI will bring formal verification, which for decades has been a bit of a fringe pursuit, into the software engineering mainstream.
55
Our new SAM audio model transforms audio editing
We're introducing SAM Audio, a state-of-the-art AI model that enables you to segment sound.
56
GPT Image 1.5
This 2025 launch introduced a faster ChatGPT Images experience and GPT‑Image‑1.5 in the API. Explore the latest ChatGPT Images 2.5.
57
Prompt caching for cheaper LLM tokens
A far more detailed explanation of prompt caching than anyone asked for: how tokens, embeddings, and attention make cached LLM tokens 10x cheaper and faster.
58
Gemini 3 Pro vs. 2.5 Pro in Pokemon Crystal
From 2.5 Pro's lighthouse loop to 3 Pro's "Zombie Phoenix" strategy against Red: a full breakdown of why Gemini 3 Pro is a superior long-horizon agent.
59
60