foruhar
foruhar on Hacker News
Posted by
foruhar on Wednesday October 28, 2026 @03:41PM
from the diffuspace.ai dept.
Saturday and Sunday are not weekends worldwide.
Much of the middle east, Brunei, Nepal, and a few others have non-Monday-Friday work weeks.
I saw the film.
I wonder if it was part of the contract that the film makers not use the word sociopath of psychopath in the film. The closes we get to wondering if she may be "the most manipulative person."
I understand that the film should not be trying to give a psychiatric diagnosis yet it's something that I feel could have been discussed, and possibly dismissed, directly.
Posted by
foruhar on Monday September 28, 2026 @12:34PM
from the naive.ai dept.
I feel like the authors of many non-fiction books (e.g. business, self-help) are told that they must write a 320 page book, even if the core is, at most twenty, pages. I guess it needs to look plump on the shelf at the airport or something. Dale Carnegie got a lot across in a small number of pages. Today he’d have to do 320 pages or maybe even two books one on making friends and one influencing people. I wouldn’t mind paying for the book if there was a way to get the wheat without the chaff. I’ve seen various book summary apps but I’d rather get it straight from the author minus 300 pages of filler.
Posted by
foruhar on Sunday July 26, 2026 @11:01PM
from the block.xyz dept.
Posted by
foruhar on Sunday July 26, 2026 @10:59PM
from the buzz.xyz dept.
Posted by
foruhar on Thursday April 16, 2026 @10:13AM
from the arxiv.org dept.
That's a fairly decent defintion of vibecoding across multiple sessions.
Hyperbolically, I think it's one of humanity's greatest resources. I can find anything from precision machining, LLM internals, historical footage of WWI, music performances from pretty much any era, and on, and on. There are so many things that I didn't know there was any footage of or that I didn't a single thing about that I find there pretty much daily.
I wish the BBC would publish their whole archive through YT. The few things that they do put up are often so mind expanding whether it's Berty Russel, The Beatles, or some cracking Scottish chap going for a bike ride with a bottle of whisky.
Posted by
foruhar on Tuesday April 14, 2026 @07:49AM
from the arxiv.org dept.
Happy days at the ant colony.
Smalltalk too was originally a full OS running on bare metal back in the Xerox Alto days (1972-ish).
Tesla was the real power grid guy. The scope of his invention from the generators at Niagara Falls power generation to the transformers to the motors is pretty impressive. More so given that he was eventually given the patents (originally issued to Marconi) for radio transmission.
My sense is that the Gemini models are very capable but the Gemini CLI experience is subpar compared to Claude Code and Codex. I'm guess that it's the harness but since it can get confused, fall into doom loops, and generally lose the plot in a way that the model does not in Gemini Studio or the Gemini app.
I think a bunch of these harnesses are open source so it surprises me that there can be such a gulf between them.
Gemini-3.0-flash-preview came out right away with the 3.0 release and I was expecting 3.0-flash-lite before a bump on the pro model. I wonder if they have abandoned that part of the Pareto/price-performance.
This video shows the systems being built and shipped with cooling, cabling, etc.
It’s pretty mind blowing what this crisis shows from the manipulation of atoms and electrons all the way up to these clusters. Particularly mind blowing for me who has cable management issues with a ten port router.
https://youtu.be/1la6fMl7xNA?si=eWTVHeGThNgFKMVG
Posted by
foruhar on Sunday October 26, 2025 @01:18PM
from the github.com dept.
This interested me as a simple-ish approach to a tough-ish promblem. From the example Trip Planner file:
"""Command line interface to process a trip request.
We use Gemini flash-lite to formalize freeform trip request into the dates and
destination. Then we use a second model to compose the trip itinerary.
* This simple example shows how we can reduce perceived latency by running a fast
model to validate and acknowledge user request while the good but slow model is
handling it.
The approach from this example also can be used as a defense mechanism against
prompt injections. The first model without tool access formalizes the request
into the TripRequest dataclass. The attack surface is significantly reduced by
the narrowness of the output format and lack of tools. Then a second model is
run on this cleanup up input.
*
Before running this script, ensure the `GOOGLE_API_KEY` environment
variable is set to the api-key you obtained from Google AI Studio.
Usage:
python3 trip_request_cli.py
"""
Nifty! Is there a github or source for this?
Posted by
foruhar on Tuesday November 12, 2024 @02:23PM
from the en.wikipedia.org dept.
Posted by
foruhar on Monday April 29, 2024 @01:14PM
from the conveniencestore.co.uk dept.
Posted by
foruhar on Friday March 29, 2024 @07:24AM
from the nytimes.com dept.
Posted by
foruhar on Thursday March 28, 2024 @07:56PM
from the nytimes.com dept.
Posted by
foruhar on Saturday January 13, 2024 @02:38PM
from the thecooldown.com dept.
Iran (and some neighbors) starts the new year on the Spring Equinox, the first day of spring. It’s named Now Ruz which translates to new day. Kinda makes sense to kick off the year at spring. It’s also pretty precise give that it’s an astronomical event. It dates back to at least Zoroastrian times (15th century BCE).
All the equinoxes and solstices are celebrated there. The winter solstice is named Yalda Night, which was a few nights ago and Christmas may be related to this astronomical event. There is also Mehran and Tirgan. Ancients did like to get together and party.
https://en.m.wikipedia.org/wiki/Nowruz
https://en.m.wikipedia.org/wiki/Yald%C4%81_Night
It’s a bridge to nowhere.