albert_e

Is that memo ... technically a single sentence?

This was super useful. Thanks.

That last slide with a QR code that purports to embed the entire document/deck is intriguing.

I presume there are practical limits to the file size here?

And images inside slides must be impossible to fit it right away?

Has anyone successfully jailbroken Amazon Echo and Google Home devices to make them Claude/ChatGPT assistants without any telemetry/dependency on Amazon/Google respectively.

First impressions -- i do not quite like the physical product's shape and look.

Looks like the animated background image was sourced from: https://pislices.art/GIFS

For teams that want to use technology to the maximum, recording MS Teams meetings allows them to use copilot transcript etc. That is the most common reason I see these days.

Earlier the main reason was to allow for a human to revisit any important discussion of they missed making detailed notes. It also allowed anyone who misses the meeting to catchup. And for global teams, team members in other time zones can catchup and maybe rewatch the meeting of accent differences made following the live meeting difficult. The coworker tasked with writing the minutes (manually!) would find it super handy. We also did recordings for "requirements gathering", "design review", "prototype walkthrough", etc so we captured all feedback and nuances thoroughly so next iteration can address them all.

For all these benefits we sometimes opened a MS Teams bridge and turned on recording EVEN WHEN we were all meeting in person. I would switch on the webcam and turn it towards the whiteboard, and try to get the best clarity possible -- a service to anyone who might be watching afterwards.

Icing on the cake: the employee had a seemingly valid health-related concern about this and the employer -- a "healthcare" company -- ignored it inspite of doctor's recommendation.

Microsoft logins are automatically taking us through "creating passkey" and "failed to create a passkey" without any prompt to user or consent from user

2030: Sorry we made you sit through AI interviews.

Is there a equivalent of Handy for Android?

Soo ... you SHOULD get to the point first?

I am guessing here.

Corrections based on larger context should also be part of the streaming output -- maybe include replacement text for previous chunk/s identified by chunk ID.

What the demo does not do is show streaming output of transcribed text as we are speaking and recording (before we hit stop). That is an essential feature IMO for most general purpose live STT apps.

However ... (posted this as a separate comment earlier:)

There is contrary reporting too on whether "Logicfolding" tech is part of the deal -- https://www.huaweicentral.com/qualcomm-refutes-huawei-logicf...

> Qualcomm and Huawei have inked a new broad patent licensing agreement on AI, 5G, and networking, though the LogicFolding chip tech is not part of this deal. The US chipmaker has clarified the assertions made regarding the new chipset technology.

There is contrary reporting too on whether "Logicfolding" tech is part of the deal --

https://www.huaweicentral.com/qualcomm-refutes-huawei-logicf...

> Qualcomm and Huawei have inked a new broad patent licensing agreement on AI, 5G, and networking, though the LogicFolding chip tech is not part of this deal. The US chipmaker has clarified the assertions made regarding the new chipset technology.

Are we seeing an uptick in the number of posts/chatter around ESP32 of late?

I recently got interesed in hobby electronics again and happened to lookup what I can do with an ESP32 -- and since then there has been at least one HN front page post about ESP32 every day. Not sure if it is just a frequency illusion.

Bob ROS

This is in the same space as this creative exploration posted a few months ago -

---

Training AI to Paint with Code, March 2026

https://surya.website/rling-qwen-to-paint-with-code

HN Discussion:

https://news.ycombinator.com/item?id=49411800

Thesis presentation:

https://vimeo.com/1190839818

And I believe the HN user who created this is @kickingkeys

---

fascinating space to explore:

Instead of having AI directly generate an output, what happens if we ask AI to take a stab at the PROCESS of creating something.

Looks useful. I was experimenting with making an SVG creator tool that can churn out shapes that go beyond the shape library of microsoft powerpoint -- so my slides can stand out. Things like a hexagon with rounded corners, squircle, swooshes and blobs etc.

Patterns like these are useful as well.

The auto mode classifier has been out of service more than once in last 24 hours.

Had to shift+tab into other modes and manually approve permissions like a cave man

Security by obscurity -- such an age old anti-pattern!

I believe many AI tools like Gemini generate publicly accessible URLs when we click "Share" on any chat conversation -- and expect users to then own the lifecycle of that link

Depending on how the link gets handled -- by the browser, device OS, any hooks/plugins/extensions, aggressive telemetry, social media url previews, preload/prefetch, wrapping and url shortening, etc as it reaches the intended user -- there are countless ways in which the URL can be indexed and scraped

There was a issue not long ago when Claude artifacts were indexed en-masse by Google and other search engines

This is shockingly lax approach to data security and privacy by design

> If you accidentally send a request with say, ~700k context already accumulated in a session which is outside cache TTL, you're paying full cost of these 700k tokens.

Thinking aloud:

The harness UI should probably implement a timer that shows whether you are still within Cache TTL since your last turn of the conversation.

> What this is normally called

Is this also what Microsoft calls "Magentic" pattern?

(for a long time i kept reading it as Magnetic pattern)

https://learn.microsoft.com/en-us/semantic-kernel/frameworks...

My hypothesis:

One way to bias the generative output away from ugly generic sloppy defaults and towards something you personally prefer and desire based on your taste ... is to show it examples of what good looks like to you.

It is very hard for us to describe in words why you like a certain thing. But you can spot it when you see it. Or you can describe some aspects of it that you like or dislike after you see it -- but not before.

This approach is more accessible to casual creators -- who do not have formal training and experience to say "use corporate memphis" or "punk fanzine look with grunge typography".

(and this can apply to many fields -- not just visual design)

If this continues to be a thing ...one might actually imagine a good system where we have AGENTS.md with all generic agent instructions and a bunch of harness specific files like CLAUDE.md, GEMINI.md, and CODEX.md that all add whatever nuance and nudging each harness seems to individually require

Should we be able to manually rename those history folders to make the session history show up as --resume options in a new folder?

Fair enough.

So the chain of trust is ...

Personal credibility of the person taking the photo with iPhone (till the moment picture is taken) + tamper-evident protection against unauthorized or anonymous edits and manipulation (after the iphone photo is published and circulated)

Apple cannot (of course) vouch for the former.

AWS Fault Injection Service

https://aws.amazon.com/fis/

https://docs.aws.amazon.com/fis/latest/userguide/what-is.htm...

But alongside the marketing blitz they also offer certifications for people who are supposed to execute these projects. Even the most foundational certification exam -- which simply tests your recall on what AWS service is for compute versus networking -- teaches and tests you about "Shared Responsibility Model" that draws the line at what the customer is still responsible for when they use cloud bases IaaS / PaaS / SaaS services.

If businesses are going to cloud but without engaging / listening to competent people who know these basics -- then the blame needs to be somewhat pointed back at those very business leaders I feel.

This is not obscure magical knowledge either that is tightly controlled. Any cloud vendor will freely teach you that. Or even a google search would.

Thinking aloud about failure modes / edge cases:

If i create a high quality deepfake image, project it on a large screen and take a photo of that image with an iPhone (+apple verified image secure tag) ... would that resulting image be considered "authentic" by default?

Would digital forensics accessible to lay people still be able to fact-check and call out misuse / fakery of the new secure tag.