News for hackers. Stuff that matters.

Dramatize

Re:Triple-A Minesweeper on Saturday October 10, 2026 @04:21AM (#50030841)
The lady sounded like the voice of Celeste from Arc Raiders
Re:Show HN: Makefaster.dev on Sunday September 13, 2026 @07:52PM (#49690032)
Will check it out

Show HN: Ambient Context v1.0.0 (Missing context for AI assistants)

https://github.com/dragthelake/ambient-context/releases

The other week I posted a concept to use the macOS Accessibility API to capture the text on your screen into a markdown file. It seemed to be interesting with 150+ github stars.I've done a bunch of updates and packaged them into a signed macOS app.One of the biggest changes was moving away from 'one context file per day' to three markdown files for apps, website, and messages.I then run Andrej...

( Read More... | no comments | 2 points | on HN )
I've released the v 1.0.0 with a bunch of improvements + a signed app. It's the first time I've done this, so still working out exactly what's required: https://github.com/dragthelake/ambient-context or ambientcontext.app
Update: I've added a prompt to process the raw output into something more useful: https://github.com/dragthelake/ambient-context/blob/main/doc...

This is pretty magical tbh

Also added MIT license and added some more pruning to reduce initial capture by around 10%.

Oh interesting, I'll check it out
Appshots is fine for what it is, but not great for building ambient context about your daily usage/work.
One app that's using this technique (not exactly sure if it's the same) is Littlebird: https://littlebird.ai/

I also saw that HeyClicky started doing something similar but end up removing from the product.

Because you then have the macOS orange screen sharing warning/icon. I don't really want to record my screen, just the text is enough.
Yeah don't get your hope up too much. I need to push through more cleaning up of what's captured. Let me know how it goes, keen for some feedback

Show HN: Screen memory without screenshots, just text to Markdown

https://github.com/dragthelake/ambient-context

It's a macOS menu bar app that reads the text of your focused window every few seconds through the Accessibility API. No screenshots, no video, or OCR. It writes plain markdown, one file per day, into a folder you choose.Point Claude Code (or anything with file access) at the folder and ask "what did I work on Tuesday?" or have it build memory about your projects. The folder contains an...

( Read More... | 26 comments | 35 points | on HN )
My son gets too distracted by any screen (we have had to implement a total screen ban), so screen-based learning doesn't work after a few days. Is there a way to create an analogue paper version? ie with printer and scanner.
Re:Effective YouTube Kids: Quality Content in Small Doses on Wednesday July 03, 2024 @07:36PM (#40871088)
I've been thinking of doing something like that with a Synology
Re:Effective YouTube Kids: Quality Content in Small Doses on Wednesday July 03, 2024 @05:49PM (#40870316)
I found the best way to deal with YouTube is to download the videos and airdrop them to my son's iPad.

This way he can still view a selected range of Minecraft videos without getting stuck in the cesspool of '100 days as a chicken' playlists.

Re:Show HN: DataSheetGrid, an Airtable-like React component on Saturday November 11, 2023 @03:20PM (#38234118)
I will check this out. I was playing around with https://grid.glideapps.com/ for a project.
Re:Show HN: Simple Bulk GPT Generation from CSV on Sunday August 27, 2023 @10:20PM (#37288918)
Too early to tell yet. Here's an example of the content: https://www.standardretail.co/glossary/revenue-per-visitor-r...

I've only just submitted the site to Google and waiting on indexing.

Show HN: Simple Bulk GPT Generation from CSV

https://github.com/dragthelake/Bulk-CSV-to-GPT-Processing

This is a simple app that's saving me lots of time.I normally use Google Sheets to generate bulk GPT content. The problem I had was GPT4 would time out.This app takes a CSV files of terms and uses with a separate prompt text file.Just add your OpenAI API key and you're good to go.Happy for any feedback.

( Read More... | 3 comments | on HN )
Re:15.ai on Monday June 13, 2022 @12:13AM (#31721020)
Do you still ban users from using different AI voices together?
Re:iOS 16 on Monday June 06, 2022 @11:03PM (#31649409)
But can I remove the torch icon from the lock screen? I hate it so much.
Re:Ask HN: What game do you wish existed? on Wednesday May 25, 2022 @05:10PM (#31510596)
That sounds like Elden Ring.
We (Replica Studios) are releasing a major quality update next year. Here's a preview: https://replicastudios.notion.site/Preview-Voice-Quality-Upd...
Re:Ten years of OP-1 on Wednesday April 14, 2021 @07:45PM (#26814539)
I first purchased an OP-1 because of the YouTube demos, but end up selling after a few weeks.

I've now got a Digiton/Digitakt setup that's much better. Elektron's workflow just clicked with my brain.

Re:Lyebird: Clone Your Voice on Wednesday September 09, 2020 @04:34PM (#24425623)
Zohaib and I can always be found on these threads :)

The two main non Google/Amazon competitors are https://www.resemble.ai/ and https://replicastudios.com/

Re:Heyyyyyyyyyyyy.com on Wednesday August 26, 2020 @01:01AM (#24279276)
Signed up and reserved my email.
Re:Zappos CEO Tony Hsieh is stepping down after 21 years on Tuesday August 25, 2020 @08:41PM (#24277896)
Also in Australia. That's exactly the same strategy I used growing the initial version of 99 Bikes ecommerce store. CDBaby was also a big influence.
I think you're going to have legal risks with a project like this. At some point a celebrity is going to sue and we'll find out what the law decides.
Yep, that's what we're doing at https://replicastudios.com - though we have strict ethical guidelines to not clone a person's voice without their permission.
America elected a reality TV personality to be President.

Older »