smnscu

I do something similar but a bit more involved, using a few informal stages. Let's say for example I'm trying to launch a new complex feature for https://coderba.se.

- strategy document

- "sprint" document with technical implementation

- actual implementation

- e2e testing scenarios updates

Every step involves iterating with Claude on it with me in the loop (setting the direction then resolving the "founder questions" as they appear), and importantly a different model for review/code-review, be it Codex (usually, it's great at it) or Antigravity/Gemini (sometimes finds novel things, its precision and recall are abysmal but on the odd occasion it has good accuracy). This iteration on the high-level plan then on the implementation plan is essential to me, and IMHO part of why people are surprised that I tend to get solid results from LLMs. At the very least, it allows me to fill gaps in my own knowledge (primarily front-end development) and be more productive than writing the code myself. I cannot stress enough how nice it is to have a partner in the high-level system design – yes, it often suggests utterly moronic ideas, but the overall experience is still net positive and getting better every quarter.

I thought Common Side Effects was great, then I watched Scavengers Reign. Absolutely mindblown. Possibly the best scifi _thing_ I've ever watched.

There's still hope for a second season FWIW. At least the story is mapped up, if not more preprod stuff, it's been a while since I looked into it.

I'd be curious how it handles someone parking poorly in that bay e.g. diagonally. Presumably those lines serve as a parking guide and the door won't close unless you park correctly.

Presumably Goldman Sachs (or any investment bank worth its salt)

I was thoroughly confused at why the website was showing the weather for York. Since I studied there (and it's straight up a lovely place), I visit quite often and subsequently check the weather. I thought I had set it but couldn't remember doing so. As someone else said, this being text-based makes it particularly digestible to LLMs. Out of curiosity, I looked up weather MCPs and stumbled upon this: https://github.com/weather-mcp/weather-mcp

I am building an interviewing and hiring platform (https://coderba.se/) but I've also hired/interviewed and shaped hiring processes at several companies before. It's ridiculous how easy it is to account for such trivial edge cases, yet most people just... dont. A big part of it is that, in spite of frequent chest beating about how "hiring is [one of] the most important thing[s] we do", the actual process is half-assed at best in most places, an effect particularly amplified by the current massive oversupply of talent.

This entered the daily rotation (currently dominated by NYT Games) for our wife and me, thank you!

Firecracker is fantastic technology. I'm using it for my interviewing startup to run isolated runtimes for coding interviews (and personal workspaces), and it's been rock solid and incredibly lightweight. Interfacing with it through the Go SDK has been a piece of cake, too.

Quick NPR Short Wave episode about this https://www.npr.org/2026/05/27/nx-s1-5806598/disease-science...

Nice post! You piqued my curiosity, so after a bit of research it turns out that, with techniques like MTP/MLA/CSA, it's quite probable that these models are much more efficient (and maybe bigger? tho 400B sounds about right) than a simple RAM breakdown would suggest.

MTP - https://blog.google/innovation-and-ai/technology/developers-...

MLA - https://machinelearningmastery.com/a-gentle-introduction-to-...

CSA - https://deepseek.ai/blog/deepseek-v4-compressed-attention

That's me with Google Antigravity. Switching back to vscode was such a breath of fresh air. Porting over my (extensive) settings/extensions/keyboard shortcuts was extremely easy too (just ask the agent to do it), and now I can use both Copilot models and Claude Code easily. More to your point though, the speed and stability is incomparable. I can't remember having many issues with Cursor last year when I used it at my last job, but still, vscode has been surprisingly pleasant for agentic use.

I'm working on Coderbase (https://coderba.se/), a platform for running technical interviews. It started with live interviews cuz that's what I know best, having run over 3,000 interviews in my career, but I made it easy af to run this yourself too. I initially pictured it as a tech-heavy product (and it is), but my second client is a large recruitment agency that's using it both for internal interviews (for recruiters) and external ones (for candidates they're presenting to clients).

I didn't set out to do this. After I got laid off in December, a client quickly fell in my lap: a small startup in the middle of a massive investment round that needed to hire 25 people immediately, with only a CTO available for interviews. I created their content and ran their interviews while building the software at the same time. It started as Google Meet + CoderPad + Calendly and gradually became an in-house system. Unlike Proton (lol), I'm not pretending I built my own video call solution from scratch, it's just an off-the-shelf 100ms integration.

The content is all versioned and structured, which makes it fast to iterate on and easy to reason about. We use major.minor versions and only bump the major for backwards-incompatible changes, or changes big enough that comparing interviews stops making sense. Otherwise, any combination of question versions inside an interview format is considered comparable if the major versions are identical.

The interview itself is highly structured: once you define a format from the content library and the various knobs you can adjust, you can schedule interviews and run them using our integrated "room" (video call + multiplayer code editor, both recorded, with transcripts and playback) and "rubric" (the tool the interviewer uses for content, scoring, and notes during the interview). Once you submit/publish the interview, a report is generated immediately. Example: https://coderba.se/sample

Two interesting AI bits:

- "AI linting": a way to benchmark interview questions by running a candidate model and an interviewer model against each other. The candidate closely follows a defined skills profile, then we compare actual vs expected performance. More here: https://coderba.se/blog/product-update-unit-testing-the-inte...

- "AI draft": once an interview ends, it takes ~30s for the video and transcript to become available. Then we use basically every relevant artifact from the interview, with a PII redaction pass first: questions, scoring, incomplete rubric, transcript, code editor history. We send that through our LLM gateway, currently mostly using DeepSeek because the quality/value is insane, though I may switch to Mistral to stay on the better side of privacy. It sends back recommended scoring + writeup, which we present as Cursor-like suggestions you can accept/reject/edit.

I've been through the exact same migration path and I'm so incredibly happy with Better Auth. Good reminder that I should contribute: https://better-auth.com/docs/reference/contributing

Hey HN, wanted to share an early peek at what I've been building over the past few weeks.

I've spent the last 7 years conducting over 3,000 technical interviews. Along the way, I made the (utterly insightful) observation that most hiring processes are broken, often relying on vibes and ad-hoc trivia. Coderbase is in large part my attempt at treating hiring and interviewing as a rigorous systems engineering problem rather than a simple outsourcing of the thick side of the hiring funnel.

I'm essentially attempting to distill thousands of hours of interview data into sensible processes that can lead to meaningful improvements to hiring. The platform underneath it all is early, but we're getting close to being able to scale the system to e.g. 1000 interviews per week without (hopefully) breaking a sweat.

I plan to publish these weekly, as working on this technical challenge is exhilarating (I already have enough material for a second post but it's got to wait until next week). For now, let me know what you think of my attempt to weaponise AI slop (aka "synthetic interview benchmarking").

Otta in the UK (now eaten by the inexplicably-named Welcome to the Jungle) used to have a very involved vetting process during company onboarding, and I could verify that it was a great service as both a candidate and a hiring manager. To replicate what you want ("every listing is verified") there's no silver bullet but a good vetting process like that goes a long way.

Another site I like is cord.com, which seems to prioritise companies where recruiters are active on that website, I've had a good experience with that one as well, as you get to chat with an actual recruiter in a matter of hours or days.

Obligatory "this is why I love HN" but even for that standard, this is is an incredibly open account, thank you for the insight and sorry it hasn't seemed to pan out quite how you hoped. Still sounds like you got your bag, built something cool, and have your "micro" share of Internet legacy, so not too bad eh?

Quite chuffed someone else mentioned Djokovic, who is close to 39 and just played an Australian Open final. (Yes he got lucky with 2 freebies but he _did_ beat Sinner in the semifinal fair and square, and managed to win the first set before running out of juice)

> After go-micro‘s maintainer went off the rails

What do you mean by this? Genuinely curious, as someone who's followed that project in the past.

I've interviewed 3k people with Karat as a professional interviewer, and several hundred more as a hiring manager. The very few times I received direct emails from candidates attempting to circumvent the normal process were met with unequivocally negative reactions. First, I find the Internet sleuthing they'd undergo to find my email address a bit creepy – for example, Karat would only show the first name and profile pic for your interviewer. But more importantly, the sheer audacity to go for such a stunt would firmly anchor them in the box of people I'd never want to work with. I'd still be polite and professional to a fault, of course, but I'd never seriously consider them past that point.

This is a strong contender. Other candidates (hard to find links to the first editions):

- https://www.goodreads.com/book/show/11177063-creating-cool-w... - https://www.goodreads.com/book/show/1097095.HTML_for_Dummies...

I've been calling this context.md in my projects (alongside a progress.md for TODOs and breaking down complex tasks). I don't care what we call it as long as we settle on a convention.

I use it mostly as smarter autocomplete and it's still absolutely worth it. I really tried having it write unit tests in Go, write simple Astro websites, etc, but I'm never satisfied with how dumb it is when "vibe coding", so I use it as Intellisense on steroids for now, but I don't doubt it will become even better soon. The chat feature is fantastic and between it and the contextual help I barely ever have to reach for actual (code) documentation.

Drama aside, I thought I'd share a fun fact with the youngins: John Gruber (yes, the Apple blog guy) is the creator of Markdown. Thanks, John!

Having used Go professionally for over a decade, I can count on one hand the times I used recover(). I've actually just refactored some legacy code last week to remove a panic/recover that was bafflingly used to handle nil values. The only valid use case I can think of is gracefully shutting down a server, but that's usually addressed by some library.

I used to do thousands of interviews across the industry and I vividly remember Apple backend devs being almost always unmitigated disasters. They would always pick Java and could barely use it - to the point where a for loop would be challenging. Their Swift guys were fairly decent though IIRC.

Here's a potential starting point: https://tech-coops.xyz/

Fairly often you see service-focused small companies (i.e. agencies) being run as coops, e.g. my friend's NZ .NET shop http://iontech.nz/

Oof, must suck to work for a company who doesn't use technical design docs well. I quite like Oxide's RFD model, based off Joyent's I assume, given who their CTO is. https://rfd.shared.oxide.computer/rfd/1

I've just recently this video on the engineering of Venice: https://www.youtube.com/watch?v=77omYd0JOeA -- relevantly, it shows how they devised an "active" drainage system that relied on the tide movement (both vertical and horizontal). The timestamp for waste management is 7:45, but I recommend watching all the video.

Enjoy https://www.srenity.online/

Nice, adding these to my list. Here's a list that I put together, it has active GitHub projects for LLM UIs, ordered by stars:

- https://github.com/nomic-ai/gpt4all

- https://github.com/imartinez/privateGPT

- https://github.com/oobabooga/text-generation-webui

- https://github.com/FlowiseAI/Flowise

- https://github.com/lobehub/lobe-chat

- https://github.com/PromtEngineer/localGPT

- https://github.com/h2oai/h2ogpt

- https://github.com/huggingface/chat-ui

- https://github.com/SillyTavern/SillyTavern

- https://github.com/ollama-webui/ollama-webui

- https://github.com/Chainlit/chainlit

- https://github.com/LostRuins/koboldcpp

- https://github.com/ParisNeo/lollms-webui/