I'm pretty sure a good portion of Canva is vibe-coded too. You could argue Canva has tests, QA, etc. But somehow I feel we just tend to associate quality to commercial products.

:) this is the truth, every single developer I knew moved away from coding by hand every single one.

Well you don‘t know me, but you can still feel free to count me against your stats

Well seems like you don't actually know any good developer

Sound like Google suffered from FOMO and felt the urge to appear in the hacking news, along the big AI players. No way Gemini is state of the art, but perhaps it's where Claude and OpenAI were 6 months ago, which would be not bad at all.

They all want that regulatory capture so badly.

It’s embarrassing anyone is falling for this.

I think Gemini focused on integration and practical goals instead of coding intelligence.

It doesn't look it was their decision to announce this, and regardless it happened -- hopefully no one thinks that they got Irregular to permit yet another accidental hack just so they could cop to it months later as a marketing ploy.

Y'all, it's Google. They own a money printer and the boring ~half of the AI field. They don't need these weird games to influence the government, and regardless, there is precisely a 0.0000000% chance of regulation happening before Trump's ouster anyway.

So please take it seriously. I'd like us all to survive this, ideally :/

Really interesting to see how many cosmogonies proceed in stages, with the sea at the beginning of creation, and animals/plants/mankind appearing later.

Thanks to science we know it's more or less what happened (plus evolution) but it's nice to see how pre-scientific intuition somewhat worked it out.

I went through the "myth in human history" class/book from The Great Courses some years ago (great course!), iirc it mentioned a few common themes of creation myths: cosmic egg, emergence from depths, divine parents, ex nihilo, and "retrieval from the sea bottom".

I think any relation to actual science is accidental.

What are the use cases for this? On other words, what problem(s) does it aim to solve?

I am the author of fileregister. fileregister is a cross-machine tagging system (macOS, potentially Linux). fileregister keeps durable ids (bookmarks) for a file in a plain-text JSONL-file. Now you can move the files around or rename them and the link will not break. On top of that you have markdown sidecars where you can store additional data to any file. This can serve as a binder of files which belong together. This can be used to build photoalbums or collect files which are spread over the filesystem. The essential metadata is saved in the attributes of the files so you can search for the file with Spotlight. The macOS-filesystem-anchor can be replaced by a Linux-filesystem-anchor. As the yellow book of the files is stored in a JSONL-file it can be marshalled (packed) and unmarshalled (unpacked) on another machine and the links remain intact.

Reading helps: https://github.com/rhsev/fileregister#what-you-can-do-with-i...

I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time.

Using both OpenAI and Anthropic models, Cursor is cheaper than having two separate subscriptions, and their free tier of Composer is good enough. I will now have to reconsider my options.

JetBrains is a good option - works with any model/agent. Also they have very good semantic search for the codebase, which is exposed via MCP to the agents.

Jetbrains Air is a great agentic coding harness

If only they would update it to work with their remote development kit... One can keep dreaming right :)

currenly I use pi with openrouter and is very nice I combine with a chatgpt sub that allows me to use it with pi. and when my usage runs out I turn to openrouter. Then same when I need anthropic models

It's very easy to achieve that and more with: Crush (or Opencode) + OpenRouter right from the terminal. Takes a minute to setup.

If you can explain how to make compaction not suck in opencode or Kilo Code, I would love to know how. I am really trying to make use of other harnesses but that's a major sticking point.

Never compact. Not automatically, not manually. Instead, let it write ledgers and checklists or handover prompt if necessary, and start fresh sessions as often as possible.

What do you do for long-running goals / tasks where you are not interactively prompting?

Create a design spec and implementation plan first. If necessary, split that in phases. Then create a ledger that always holds the current status, and instruct the model to update that after it completes a task in the plan, and to append any issues it encounters during the implementation.

Then you can let it run, and when it stops, point a fresh session to the ledger to pick up the work from where the previous one left off.

You can get more fancy by using something like GitHub issues for coordination too and have multiple sessions create issues and epics and others to work on that in isolated worktrees, but the spec-plan-ledger approach usually works great for small to medium large projects.

second this notion, fresh sessions and markdown are far superior to compaction, which has high likelihood of wrecking the context

AmpCode is not popular here but I recommend it, give it I try and you will not go back, except the price may a bit expensive.

you can still bring your own OpenAI key into Cursor. that is not going to change.

In Antigravity you can install Codex and use both. Not sure if the Claude extension can work too but probably.

I like Cursor. Honestly the biggest reason is the decent WYSIWYG markdown editor.

Isn't the markdown editor in Cursor just vanilla VS code?

Nope. VS renders in a separate tab but is not editable. There are a million plugins, but some are still not good or look sketch.

How is it different from the Oyster card in London?

Suica works virtually everywhere https://www.jreast.co.jp/multi/suicamoney/shop.html

Imagine if you could pay with the Oyster card everywhere from Tesco to Greggs to National Rail to Uber

Actually you can find some small family shops, restaurants etc where they don't accept credit cards but Suica only

Isn't that patent similar to CodeAct [1], originally described in this paper [2]?

[1] https://learn.microsoft.com/en-us/agent-framework/agents/cod...

[2] https://arxiv.org/abs/2402.01030

Very nice project, thank you for sharing it on HN! May I ask why login is required, and how are emails/passwords stored?

An account is necessary to couple your devices to your wall. And auth is implemented via Better-Auth. I stopped Codex immediately when he tried to implement the login stuff from scratch. :)

I've never seen the word "cyber" sprinkled so generously.