News for hackers. Stuff that matters.

myyke

Not yet on Hugging Face though.

Show HN: Aiaiai.guide: Plain-English mental model for LLM apps, tools and agents

https://aiaiai.guide/

I’ve been building LLM tooling for a small VC fund and found myself explaining the same mental model over and over to non-technical people around me: how a stateless LLM becomes a chatbot, how tool use works, what an agent is mechanically, and why context windows shape all of it.I never found a guide that covered that full chain at the level I wanted, so I wrote one.It’s nine short chapters,...

( Read More... | no comments | 2 points | on HN )

Show HN: tintcd – directory-aware terminal theming for PowerShell

https://github.com/ymyke/tintcd

I built a PowerShell module that hashes directory paths to generate unique background colors. Each folder gets a stable, deterministic tint – no configuration needed.Why? I always have several terminal windows open in different folders. I'd alt-tab back, squint at the prompt, and wonder if I'm still in the right place. The prompt alone wasn't enough. I wanted something low-effort: no manual...

( Read More... | no comments | 2 points | on HN )
Re:Ask HN: How can archive.is access paid online articles? on Friday December 19, 2025 @07:15AM (#46324991)
There seem to be issues indeed:

On October 30, 2025, the U.S. Federal Bureau of Investigation (FBI) subpoenaed Archive.today's domain registrar, Tucows. The subpoena stated its purpose is to identify the owner(s) of the archive.today domain name, and that it was part of a criminal investigation conducted by the FBI, the nature of which was not disclosed.[8][9]

https://en.wikipedia.org/wiki/Archive.today

Ask HN: What is "response-level error rate" and how is it measured?

There's this chart around gpt-5's hallu and error rates:https://api.wandb.ai/files/byyoung3/images/projects/37269171/0da61431.pngfrom:https://wandb.ai/byyoung3/ml-news/reports/GPT-5-Benchmark-Scores---VmlldzoxMzkwMTYyMgI'm wondering what "response-level error rate" is exactly and it is measured?gpt 4.1 says it's sampled production prompts, rated by humans. Is that it?

( Read More... | no comments | 2 points | on HN )

Show HN: Witmo – AI-powered gaming coach from screenshots

https://github.com/ymyke/witmo

Hi HN, I’d like to share a project I’ve been working on: Witmo – an open-source, terminal-based tool that gives you in-game advice by analyzing screenshots from your gameplay.I created Witmo after picking up Elden Ring and constantly running into questions mid-game. I wanted a tool that would let me quickly get advice based on a screenshot — without having to type long explanations for an LLM...

( Read More... | no comments | on HN )

Ask HN: Opening Links in Correct Browser Profile from Native Apps?

I use two Edge browser profiles simultaneously on Windows—one for personal and one for work-related activities, each logged into separate Google accounts.I also have Superhuman and Vimcal configured with both accounts and open in each browser profile. In these web apps, links open in the correct corresponding profile.However, when using the Windows native apps for Superhuman and Vimcal, links...

( Read More... | no comments | 2 points | on HN )

Ask HN: Opinion please ― What are the best meeting transcription tools?

I'd like to start using a transcription tool like fireflies.ai regularly. But there are so many out there now (grain, notta, avoma, bluedot, tldv, ..., ...) that I'd love to get some guidance on which ones stand out.What I'm most interested in:- Stellar UX- Very simple and reliable to integriate into all the video call platforms out there- Great at deriving the real essentials from what was...

( Read More... | 1 comment | on HN )

Ask HN: Download Docsend

I'm using a browser extension to download Docsend files that have download disabled.It's working great but it's no longer available and I can't find an alternative.⇒ Is anybody aware of either browser extension or Python library that can download docsend files?

( Read More... | no comments | on HN )

Ask HN: Python library for robust URL retrieval with workaround strategies?

Background: I'm scraping various URLs, but (as expected) encounter issues with some servers blocking the scrapes, leading to errors like timeouts or 403 forbidden responses. Currently, I'm using the requests library, but for problematic URLs, I've noticed switching user agents or using different tools like pycurl or wget can sometimes bypass these blocks.Question: Is there a Python library that...

( Read More... | 1 comment | on HN )
Ah, now I get it, thanks, makes sense.
I don't get it; what is this for? What is the use case?

Show HN: Tessa – simple access to price information of financial assets

https://github.com/ymyke/tessa

Doing my private portfolio review with the help of tessa right now so I thought I'd post it here in case there are others who need something like this.""" tessa is a Python library to help you easily search asset identifiers (e.g., tickers) and retrieve price information for assets from different sources such as Yahoo or Coingecko. It takes care of the different APIs, caching, rate limiting,...

( Read More... | no comments | on HN )