31
Postmortem for Kernel Soundness Bug #14576
Leonardo de Moura — Creator of Lean and Z3
Most cited
Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 106 posts.
32
I’ve banned query strings
I don’t like people adding tracking stuff to URLs. Still less do I like people adding tracking stuff to my URLs.
33
The new rules of context engineering for Claude 5 generation models
We removed over 80% of Claude Code's system prompt for more advanced models. How to apply the lessons we learned to your own context engineering in Claude Code and with your own agents.
34
Natural Language Autoencoders: Turning Claude's Thoughts into Text
AI models like Claude talk in words but think in numbers. In this study, we train Claude to translate its thoughts into human-readable text.
35
Scaling long-running autonomous coding
We've been experimenting with running coding agents autonomously for weeks at a time.
36
Bun 1.4
Bun 1.4 rewrites Bun in Rust, ships built-in headless browser automation (Bun.WebView), Bun.Image, Bun.markdown, JSON5, JSONL, Terminal and cron APIs, Node.js 26.3.0 compatibility with 1,517 newly passing tests, parallel test and run, Windows ARM64, and an opt-in global virtual store for up to 7× faster installs.
37
Benchmarking coding agents on Databricks' multi-million line codebase
Databricks shares results from its internal coding benchmark, evaluating coding agents on a multi-million line codebase to optimize engineering cost and performance.
38
Why we built our own background agent
The craft of engineering is rapidly changing. We built our own coding agent to accelerate faster. Inspect is now open to teams outside Ramp through early access.
39
Mine, a Coalton and Common Lisp IDE
By Robert Smith mine is a brand new IDE for Coalton and Common Lisp, built from the ground up with one purpose: To make Coalton and Common Lisp easier and more accessible to the programming world. TL;DR? Go to mine's homepage with downloads for Windows/macOS/Linux. mine is a complete, single-download application that…
40
A sufficiently detailed spec is code
Specifications do not address the limitations of agentic coding
41
Breaking the spell of vibe coding
Sinister variations on the positive state of flow
42
43
44
Things Unix can do atomically (2010)
This is a catalog of things UNIX-like/POSIX-compliant operating systems can do atomically, making them useful as building blocks for thread-safe and multi-process-safe programs without mutexes or read/write locks. The list is by no means exhaustive and I expect it to be updated frequently for the foreseeable future.
45
Zig 0.16.0 Release Notes
Zig is a general-purpose programming language and toolchain for maintaining robust , optimal , and reusable software.
46
You need to rewrite your CLI for AI agents
Human DX optimizes for discoverability. Agent DX optimizes for predictability. What I learned building a CLI for agents first.
47
Rathbun's Operator
First, I’m a human typing this post. I’m not going to tell you who I am. Sure, many will say that is cowardly and fair, but I actually don’t think it would bring much value. What matters more is that I describe why, and what I did and didn’t do during the last two weeks or so with the OpenClaw agent I set up, known as…
48
Which programming languages are most token-efficient?
Comparing token efficiency across 19 popular programming languages using RosettaCode data - from Clojure to C, there's a 2.6x difference.
49
Async Rust vs RTOS showdown (2022)
It's time for another technical blog post about async Rust on embedded. This time we're going to pitch Embassy/Rust against FreeRTOS/C on an STM32F446 microcontroller.
50
Google API keys weren't secrets, but then Gemini changed the rules
Google spent over a decade telling developers that Google API keys (like those used in Maps, Firebase, etc.) are not secrets. But that's no longer true.
51
Qwen3.6-35B-A3B: Agentic coding power, now open to all
Qwen offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
52
Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
Muse Glimmer is a 30-billion-parameter open agentic model from Meta Superintelligence Labs, optimized for always-on local workflows on consumer hardware.
53
Qwen3.8-Max: A New Bar for Coding and Cowork
Qwen offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
54
Redesigning source control at Anthropic
As our merges per day grew more than tenfold, source control became our biggest development bottleneck. Here, we share how we migrated to an in-house version control system in five months.
55
Changing how we develop Ladybird
Ladybird is changing how code enters the project as we prepare to ship a browser to real users.
56
GPT‑5.3‑Codex‑Spark
Introducing GPT-5.3-Codex-Spark—our first real-time coding model. 15x faster generation, 128k context, now in research preview for ChatGPT Pro users.
57
The session you cannot take with you
Inference APIs are filling sessions with encrypted reasoning, hidden search results, opaque compaction, and encrypted subagent messages. A growing form of lock-in.
58
A Decade of Slug
What is now known as the Slug Algorithm for rendering fonts directly from Bézier curves on the GPU was developed in the Fall of 2016, so this year marks a full decade since its inception. I published a paper in JCGT about the technique in the middle of 2017, and my company sold the first license for version 1.0 of the…
59
A Preview of DuckDB v2.0
DuckDB 2.0 is coming this fall. In this post, we preview its headline features: DuckDB as a server, triggers, the VARIANT type, asynchronous I/O, a new SQL parser, a new storage format, and much more.
60
The Zig project's rationale for their anti-AI contribution policy
Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues. No LLMs for pull requests. No LLMs for comments on the …