Skip to content

AI coding

Everything about AI writing code: coding assistants, vibe coding, code model evals and new developer workflows.

1,426 picksRelated topicsAgentsCursorTutorials

Latest picks

441–460 of 1,426

Aug 23Sunday

Hacker News front page

Prime Intellect ran 153 autonomous NanoGPT optimizer runs across 18 frontier models

Prime Intellect ran a speedrun where 18 frontier models, each paired with a coding agent harness, autonomously optimized a NanoGPT training script to minimize validation loss. Fable 5 with Claude Code reached a loss of 2,726, closing 81.7% of the gap from the human baseline to the optimal record. Opus 5 and Kimi K3 followed at 53.6% and 52.2%. DeepSeek V4 Pro closed only 12.3%, ranking 13th. The experiment consumed hundreds of millions of tokens, with the longest run lasting 8.7 days. Caveat: this benchmark tests a narrow skill—autonomous optimization of known code—not general capability, but it reveals how different models handle stability and exploration over long-horizon tasks. The post does not disclose the specific optimization strategies each model used or why certain runs failed.

Why it matters: Prime Intellect's speedrun pits 18 models against each other on autonomous code optimization, with Fable 5 + Claude Code posting a dominant lead. The concrete numbers, leaderboard, and methodology make this genuinely useful for agent builders and benchmark watchers.

Hacker News front page

LLMs make language choice less consequential, pushing devs toward Rust, Zig and harder tech

Armin Ronacher notes that LLMs erase the friction of learning a language, so devs increasingly pick based on speed marketing. Rust is gaining, and Zig appears in Cloudflare Artifacts (a ~100 KB Wasm Git engine) and Vercel fx, both LLM-assisted. Harder tech like DWARF, eBPF and custom crypto is now accessible to more people. His take: more slop, but also more devs who want things fast and small.

Why it matters: Armin Ronacher observes that LLMs cut the cost of switching languages, so developers now pick by speed claims, Rust use is growing, and Zig shows up in LLM-assisted projects like Cloudflare Artifacts and Vercel fx.

Aug 22Saturday

Hacker News front page

Software has no excuse to be slow anymore — Dan Luu shows AI makes deep perf work cheap

Dan Luu took FRE, a regex engine built by an agent loop over a month, and had AI wire AOT compilation into ripgrep in minutes — 2–4× faster on long queries, ~7% on real mixed queries. He also built the world’s strongest Azul AI with zero game-AI background using GPT-5.1/5.2-era models, winning mostly on cheap-to-him-now optimizations like multithreading and native compilation. Marc Brooker and Michael Malis agree: JIT compilers, custom indexes, and other formerly rare-skill work can now be done by anyone typing a few sentences. The post doesn’t give full holdout benchmark numbers for FRE or Elo/match counts for the Azul AI.

Why it matters: Dan Luu had AI add FRE's JIT to ripgrep, cutting long-query times 2 to 4x while his own mixed queries gained only about 7%.

Aug 21Friday

AI HOT (Curated Pool)

Anthropic publishes the AI-Native SDLC playbook, showing how it builds software with Claude

Anthropic open-sourced its internal playbook for building software with Claude, covering every phase from requirements and design through coding, testing, and ops. The post lays out concrete practices and team structure shifts. No quantitative benchmarks are disclosed—treat this as a methodology guide, not an independent evaluation.

Why it matters: Anthropic open-sourced its internal handbook for building software with Claude, covering requirements, design, coding, testing and ops, including model-run design reviews and auto-generated test cases.

Hacker News front page

Stop Making TUIs: AI-Generated Native GUIs Are the Real Deal

The author built 7 native macOS apps with AI, from a Markdown viewer to an Apple TV remote, without writing a single line of UI code. He argues the TUI era should end: just screenshot a design and give it to Claude. The post doesn't provide performance or compatibility data, but shows real integrations like SQLite backends, virtual filesystems, and embedded LLM agents.

Why it matters: The author built 7 native macOS apps, including a Markdown reader, music player and Apple TV remote, by feeding screenshots to Claude for SwiftUI, writing no UI code by hand.

Hacker News front page

OpenRouter lists anonymous reasoning model Ox Alpha, currently free

Ox Alpha is an anonymous third-party reasoning model focused on coding, long-horizon agentic work, and production workloads. It's currently free on OpenRouter with a 1M context window, 1s P50 latency, and 69 tok/s throughput. The post doesn't disclose who built it, parameter count, or how long the free tier lasts. Usage data shows Claude Code and Nous Research's Hermes Agent already pushing significant token volume—treat it as a coding agent model worth testing, but anonymity and free pricing make long-term reliability uncertain.

Why it matters: Anonymous reasoning model Ox Alpha is free on OpenRouter with a 1M-token context, aimed at coding and long-running agent tasks, at 1-second P50 latency and 69 tokens per second.

Aug 20Thursday

Hacker News front page

Slack Code turns AI coding into a multiplayer team activity

Salesforce added Code channels to Slack so coding agents like Claude Code, Devin, and ChatGPT can write code, show diffs, and run live previews inside a channel visible to the whole team. Channels are project-based and auto-archive when done. The post does not disclose pricing or launch date.

Why it matters: Slack added a code channel type where coding agents post diffs and live previews, so the team's work stays visible and gets archived automatically.

Hacker News front page

Building a custom watch face on a $27 PineTime with Claude

Mike Kasberg used OpenCode with open-weight models—Kimi K3, K2.6, DeepSeek v4 Pro and Flash—to build a Casio-style watch face for the $27 PineTime. He started by getting a build working in the InfiniSim simulator, then fed the model a reference photo to replicate the layout. The first attempt was rough: text sizing and positioning were guessed, making elements overlap and unreadable. He switched to giving isolated, concrete feedback and fixed one text element at a time. Later he turned static parts into a fullscreen 240x240 background image so only dynamic elements needed code. It worked in the simulator, but on real hardware the image took 10 minutes to transfer over Bluetooth and screen refreshes lagged 1–2 seconds; the watch can't hold the whole image in memory and streams it from flash. He calls it a working prototype, pushed the code to GitHub, and had the model summarize lessons learned into an AGENTS.md file.

Why it matters: A developer rebuilt Casio watch faces for a $27 PineTime using open models, from compiling in an emulator to fixing the layout element by element, showing model-assisted coding works on small hardware.

Latent Space

Z.ai CEO Jie Tang on GLM 5.3: The era of parameter counting is over, post-training is the new scaling law

Jie Tang posted a long thread on X arguing that parameter count alone is meaningless—you need data volume, compute allocation, and deployment conditions. GLM-5.3's gains come entirely from RL on long-horizon environments, some simulating days of engineer work. They built synthetic pipelines that auto-generate executable, verifiable environments and reward signals, pushing the model to own complex tasks end-to-end. Tang identified 5 scaling knobs including MoE sparsity, and noted that finding software vulnerabilities requires holding 20+ inference-step causal chains, not memorization. The post does not disclose GLM-5.3's exact parameter count or release date.

Why it matters: Zhipu CEO Jie Tang explains on X that GLM 5.3's gains come from long-horizon reinforcement learning, with the model diagnosing its own bottlenecks on a real cluster and delivering speedups.

Hacker News front page

LLMs turn static software into something users can extend by asking

Jeremy Morrell argues that most web apps only serve the top of the demand curve, leaving a long tail of unmet needs. LLMs now let users “speak code into existence,” so a product can keep a stable core while AI-generated extensions cover the long tail. He points to Pi and DeepSeek Harness as early examples: users ask for a feature, the system writes a TypeScript extension and hot-reloads it. The post then focuses on how to bring this to the web—traditional webhooks set the bar too high; sandboxed runtimes like Cloudflare Dynamic Workers could let non-developers safely run custom logic. No timeline or performance numbers are disclosed; the piece is a product-direction argument.

Why it matters: Jeremy Morrell argues web apps can keep a stable core and have an LLM generate and hot-load TypeScript extensions on demand, with Pi and DeepSeek Harness as examples.

Aug 19Wednesday

Hacker News front page

Ornith-1.5 uses self-generated tasks for RL, with three model sizes beating comparable open-source models on coding and agent benchmarks

Ornith-1.5 extends the self-scaffolding idea from Ornith-1.0 into a full self-improvement loop: the model proposes tasks, builds scaffolds, generates solution rollouts, and improves via RL. The 397B MoE flagship scores 86.1 on Terminal-Bench 2.1 and 56.0 on DeepSWE, matching Claude Opus 4.8 (85.0, 59.0) and beating GLM-5.2 and DeepSeek-V4-Flash-0731. The 35B MoE activates only 3B parameters per token yet outperforms Gemma 4-31B and Meta Muse Glimmer-30B on agentic coding. The 9B dense model has a quantized mobile version that runs on phones and scores 47.0 on Terminal-Bench 2.1 and 70.6 on SWE-Bench Verified, beating many larger models. Task reward multiplies validity, frontier difficulty (targeting a 20% success rate), and novelty. The post does not disclose training compute, data scale, or a release timeline.

Why it matters: Ornith-1.5 has the model generate its own tasks, build solving scaffolds and produce multi-turn answers, then iterates on that experience with RL across three sizes.

OpenAI News

Replit launches Free Mode powered by GPT-5.6 Luna, removing token costs for software creation

Replit introduced Free Mode running on GPT-5.6 Luna, so users can plan, ideate, and explore projects without tracking token spend. CEO Amjad Masad credits recent OpenAI price cuts for making the free tier viable at millions-of-users scale. Complex reasoning tasks get routed to GPT-5.6 Sol, then return to Luna while preserving project context. Sam Altman frames it as a step toward anyone with internet building a product or startup. The post does not disclose Free Mode quotas, concurrency limits, or the exact launch date.

Why it matters: Replit launched a free tier that runs everyday planning and exploration on GPT-5.6 Luna and switches complex tasks to Sol, made possible by OpenAI's price cuts.

Hacker News front page

Bun 1.4 Rust rewrite is three months late and the community is losing trust

Bun has gone three months without a stable release for the first time since 2022. Founder Jarred Sumner has been promising v1.4 since June, but dates keep slipping and community replies now openly mock the repeated 'tomorrow' promises. The rewrite moves the codebase from Zig to Rust. In the past month, 15.8k commits came from robobun, 1.6k from autofix-ci[bot], and only 790 from Jarred; he himself noted most PRs are now Claude prompting Claude. Zig creator Andrew Kelley called the original Bun code 'hacks on top of hacks' and said Jarred was writing slop before LLMs. The author argues the rewrite looks more like an Anthropic ad than a genuine memory-safety fix, pointing to the number of unsafe blocks in the new Rust code. The project now has over 5,000 open PRs, far exceeding GitHub's recommended 1,000 limit.

Why it matters: Bun has gone three months without a stable release, its longest gap since 2022, after the founder teased v1.4 in June and kept pushing it back, drawing open mockery in the comments.

Computing Life · Share · Yage

$60B for a Data Flywheel, $10M for a Working Memory

The AI race in 2026 is shifting from compute to real-world behavioral data. SpaceX acquired Cursor for $60B in stock, gaining access to coding interaction traces from over 50,000 enterprise clients—data fed directly into Grok 4.5 and 4.6 training. Google bid $10M in Spirit Airlines' bankruptcy auction for roughly 100M emails, 500M Teams messages, and 30M lines of internal code. Atlassian updated its terms to turn Jira and Confluence usage data into a continuous model-training input. DeepSeek is building its own front-end harness to capture local developer workflows that API-only access misses. The article maps these four paths—acquisition, bankruptcy purchase, SaaS terms, and self-built harness—and notes that the actual model gains from data flywheels, signal retention after de-identification, and real-world compliance friction remain unverified.

Why it matters: SpaceX buys Cursor for $60 billion in stock, taking over coding interaction records from 50,000+ enterprise customers, while Google pays $10 million for Spirit Airlines' email, messages and code, pricing work-scenario behavior data.

Hacker News front page

Purely AI-generated code has no author and no copyright under US law

This site walks founders and engineering leads through a hard legal reality: under current US copyright law, code generated entirely by AI has no human author, so it can't be copyrighted or defended as an owned asset. It cites four settled anchors—including the Supreme Court's March 2026 denial of cert in Thaler and the first rejection of a fair-use defense for AI training in Thomson Reuters v. Ross—to show the rule is already locked in. It also breaks down four common blind spots: pure AI output isn't yours, vibe coding where the AI makes creative choices leaves code unprotected, mixed codebases only protect the human-authored parts, and open-source licenses are unenforceable on code no one owns. The post doesn't offer fixes; it's a risk primer with a self-assessment quiz.

Why it matters: Under US copyright law, fully AI-generated code has no human author, so it cannot be copyrighted or protected as a company asset, which directly affects how teams using AI to write code handle ownership.

Hacker News front page

Vercel open-sourced fx, a 6.39MB minimal coding agent in Zig

fx is a Zig-based CLI coding agent that weighs 6.39MB, cold-starts in 10µs, and uses single-digit MB of memory. It's model-agnostic, runs locally or in the cloud, and compiles to WebAssembly for browser use. The design leans Unix: minimal output, no heavy TUI, built to be embedded into larger systems. Currently at v0.0.3 and marked experimental—the team warns of frequent breaking changes, so hold off on production use.

Why it matters: Vercel open-sourced fx, a command-line coding assistant written in Zig, at 6.39MB with 10-microsecond cold start, running locally, in the cloud and on WebAssembly.

AI HOT (Curated Pool)

Mojo language is now fully open source under Apache 2.0

Modular open-sourced the entire Mojo compiler and toolchain under Apache 2.0 with LLVM exceptions. All source code is now in the modular GitHub repo. Mojo hit 1.0 last week with source stability guarantees. The permissive license lets developers freely build and distribute Mojo-compiled binaries. The post does not spell out community governance or external contribution workflows.

Why it matters: Modular open-sourced the whole Mojo compiler and toolchain under Apache 2.0, a week after 1.0 shipped with a source-stability promise. Worth a look for anyone tracking unified CPU and GPU programming.

Aug 18Tuesday

Hacker News front page

Nova3D generates 3D assets as executable Blender code, not opaque meshes

Nova3D outputs Blender source code instead of a final mesh; the compiled glTF is just an artifact. All 54 benchmark items produce a valid executable program and model, each exposing named parts and a parent-child assembly tree. It satisfies 51 of 52 numeric and count constraints (best baseline: 11), defines 59 joints across 12 assets at 98.3% geometric validity, and passes 14 of 18 blinded local edits with locality preserved in all 18. Texture realism trails baked-PBR systems, but shape quality ranks second in structured domains. The key result is representational: code-native generation bakes semantic handles in at creation time, so downstream systems can inspect, measure, edit, and animate without post-hoc segmentation or rigging.

Why it matters: Nova3D has 3D generation models output runnable Blender code, so the model file is just the result and assets carry part names, assembly trees and joint constraints, skipping later segmentation and rigging.

OpenAI News

Asana cleared 5 years of engineering work in 2 weeks with Codex

Asana used OpenAI Codex to fully remove Enzyme, an outdated testing framework, from its codebase. The work was originally estimated at five years and roughly $6M; it took two calendar weeks and $12K in model and infrastructure costs. Engineers wrote a five-sentence prompt, ran up to four coding agents in parallel, and reviewed every proposed change twice a day. Asana's CTO noted that not every multi-year project will collapse into weeks, but agents make once-impossible engineering work worth attempting.

Why it matters: Asana engineers used Codex to remove the outdated Enzyme test framework, work internally estimated at five years and about $6 million, finishing in two weeks for roughly $12,000 in model and infrastructure cost.

Hacker News front page

The Benchmarkpocalypse: LLMs make benchmark hacking trivial

Dan Luu ran an agent in a loop for a month to build a regex engine. It beat the Rust regex crate by 40% on the rebar benchmark but was 10x slower on a ripgrep holdout set. He notes LLMs make benchmark hacking trivial—what once required rare expertise now takes minutes of typing. Telling the LLM about a holdout set improved generalization more than just saying 'don't cheat,' but real-world performance still lagged 4x behind on meaningful tests. He sees bogus performance claims weekly now.

Why it matters: Dan Luu's month-long AI agent loop beat Rust's regex crate by 40% on rebar, then ran 10x slower on ripgrep's real tests, putting numbers on the benchmark-versus-reality gap.