Feed aggregator

Intelligence Not Included

Hacker News - Thu, 06/11/2026 - 4:19am

Article URL: https://morrick.me/archives/10319

Comments URL: https://news.ycombinator.com/item?id=48487717

Points: 1

# Comments: 0

Categories: Hacker News

Sofle Pico Split Keyboard

Hacker News - Thu, 06/11/2026 - 4:09am

Article URL: https://www.soflepico.com/

Comments URL: https://news.ycombinator.com/item?id=48487665

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Bananagrams Tiles Word Game Online

Hacker News - Thu, 06/11/2026 - 3:56am

Here is the new game i have launched a online version of Bananagrams tiles game.

Comments URL: https://news.ycombinator.com/item?id=48487579

Points: 1

# Comments: 0

Categories: Hacker News

Ask HN: Temporal Awareness in LLM?

Hacker News - Thu, 06/11/2026 - 3:55am

I have just sent a sort of "feature request" to ChatGPT (but my question is generally applicable to most LLMs).

Here is the text, written by ChatGPT itself:

Feature request: Optional temporal awareness per conversation/project. Allow the model to receive relative elapsed time between messages (e.g. +5 min, +4 h, +2 days). This is particularly useful for long-running narrative, journaling, project-tracking, and relationship-oriented conversations where elapsed time itself carries semantic meaning.

I mostly use it for journaling, and the fact that the system is completely unaware that if I have interacted with it for 1 hour and the next message comes ... 6 hours later, something happened in between. Maybe I dozed off. Or maybe something more portentous has happened.

I suppose that not implementing this was a conscious decision, considering that any client can just send either the time with TZ or decide that only relative time is important and provide it by some other mechanism.

So what could be the reason?

- privacy concerns? - efficiency (if I use an LLM mostly to get more complete answers than I can get from Google, or to do vibecoding... then it is pretty much useless)

Or maybe it is because this time feature would impact the answers too much/consume more resources (even if this is tiny, if EVERY MESSAGE FROM EVERY USER has a slightly bigger payload or token usage, I am sure it could become a burden).

For both reason I would make this configurable at the user profile/project/thread level. But maybe I am missing other elements (including: we have already answered this 72 times and it is only thursday) and this is why I am asking here.

Comments URL: https://news.ycombinator.com/item?id=48487573

Points: 1

# Comments: 0

Categories: Hacker News

Streaming HTML

Hacker News - Thu, 06/11/2026 - 3:50am
Categories: Hacker News

Microsoft Patches Exploited Exchange Server Vulnerability

Security Week - Thu, 06/11/2026 - 2:52am

The company warned about zero-day attacks exploiting the Exchange Server vulnerability CVE-2026-42897 on May 14. 

The post Microsoft Patches Exploited Exchange Server Vulnerability appeared first on SecurityWeek.

Categories: SecurityWeek

Pages