Top all-time · #11612
Brokk
Company blog · blog.brokk.aiaiprogramming
Brokk is the company blog at blog.brokk.ai, writing about ai and programming. Since 2025, 6 different Hacker News readers have linked it 22 times, most often “A first look at GPT-OSS-120B's coding ability”. It is still writing: the last post was on 2026-10-06, and you can follow it by feed.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers cite Brokk's posts as evidence on AI coding models, such as a first look at gpt-oss-120b's coding ability and its introduced power ranking of models. Comments mostly use them as sources.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Research, benchmarks, and practical guides to AI coding agents, static analysis, code quality, and building more reliable software with Brokk.
Most-linked posts?
- A first look at GPT-OSS-120B's coding ability2 people · 3 mentions · first linked 2025-08-05
- Why Gemini 3 Flash is the model OpenAI is afraid of2 people · 2 mentions · first linked 2026-01-09
- Open Weights Coding Models in 20252 people · 2 mentions · first linked 2025-12-12
- New Benchmark for Coding LLMs puts GPT-5 at the top2 people · 2 mentions · first linked 2025-08-19
What Hacker News says?
> It eliminates any reason to use an inferior Meta or Chinese model I wouldn't speak so soon, even the 120B model aimed for OpenRouter-style applications isn't very good at coding: https://blog.brokk.ai/a-first-look-at-gpt-oss-120bs-coding-a...
Comment linking /a-first-look-at-gpt-oss-120bs-coding-ability/
on “Open models by OpenAI”Submitted Don't use musl if you care about performance as a story · 109 points
HN discussionAccording to the early benchmarks, it's looking like you're just flat-out wrong: https://blog.brokk.ai/a-first-look-at-gpt-oss-120bs-coding-a...
Comment linking /a-first-look-at-gpt-oss-120bs-coding-ability/
on “Open models by OpenAI”Submitted Mjolnir: Automated Cross-Vendor Adversarial Review as a story · 3 points
HN discussionThis is only correct if you ignore subscriptions. I ran the numbers on what you get for your subscriptions last week: https://blog.brokk.ai/a-coding-subscription-tier-list/
Comment linking /a-coding-subscription-tier-list/
on “We must pace the frontier”Submitted Why Gemini 3 Flash is the model OpenAI is afraid of as a story · 3 points
HN discussion> where are the professional tools, meant to be used for people who don't want to do vibe-coding, but be heavily assisted by LLMs? This is what we're building at Brokk: https://brokk.ai/ Quick intro: https://blog.brokk.ai/introducing-lutz-mode/
Comment linking /introducing-lutz-mode/
on “Mistral releases Devstral2 and Mistral Vibe CLI”Submitted Open Weights Coding Models in 2025 as a story · 3 points
HN discussionBenchmarked here: https://blog.brokk.ai/grok-code-fast-1-added-to-the-power-ra...
Comment linking /grok-code-fast-1-added-to-the-power-ranking/
on “Grok Code Fast 1”Submitted A first look at GPT-OSS-120B's coding ability as a story · 3 points
HN discussionOne thing we've noticed is that if you have model X implement AND review the same change, the reviewer often shares the same blind spots as the implementer. https://blog.brokk.ai/mjolnir-automated-cross-vendor-adversa...
Comment linking /mjolnir-automated-cross-vendor-adversarial-review/
on “Don't be the out of touch Kung Fu master”Submitted It's time to stop doing code reviews as a story · 2 points
HN discussionOn mobile, but I linked one of the relevant issues in my writeup here: https://blog.brokk.ai/infrastructure-for-agentic-rust/
Comment linking /infrastructure-for-agentic-rust/
on “Codex Desktop continuously generates Crashpad pending dumps”Submitted SlopCop: Forensics for Your Codebase as a story · 2 points
HN discussionFor the mj adversarial review we use a configurable coordinator (I recommend Fable) with six subagents (I recommend Luna) for specific specialties like code complexity. Narrowing down what a smaller model like Luna needs to look for / care about helps them do better work; then the larger model synthesizes and fills in any gaps. https://blog.brokk.ai/mjolnir-automated-cross-vendor-adversa...
Comment linking /mjolnir-automated-cross-vendor-adversarial-review/
on “GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?”Submitted Why Gemini 3 Flash is the model OpenAI is afraid of as a story · 2 points
HN discussionyeah, g3p is as smart or smarter as the other flagships but it's just not reliable enough, it will go into "thinking loops" and burn 10s of 1000s of tokens repeating itself. https://blog.brokk.ai/gemini-3-pro-preview-not-quite-baked/ hopefully 3.1 is better.
Comment linking /gemini-3-pro-preview-not-quite-baked/
on “Gemini 3.1 Pro”Submitted The Best Open Weights Coding Models of 2025 as a story · 2 points
HN discussionThis has similar problems to swe bench in that models are likely trained on the same open source projects that the benchmark uses. https://blog.brokk.ai/introducing-the-brokk-power-ranking/
Comment linking /introducing-the-brokk-power-ranking/
on “Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7”Submitted LLMs and Artists as a story · 2 points
HN discussionSubmitted Muninn: Code localization model in the world fits on your phone as a story · 1 points
HN discussionSubmitted New Benchmark for Coding LLMs puts GPT-5 at the top as a story · 1 points
HN discussion
