Hacker News: wskish

New comment by wskish in "OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI"

wskish — Tue, 16 Dec 2025 07:44:19 +0000

Skills are basically (on-demand) man pages for other libraries or cli tools, or SOPs for other more complex processes. A beautiful, minimal abstraction.

New comment by wskish in "GPT-4.1 in the API"

wskish — Mon, 14 Apr 2025 19:01:11 +0000

codebases of high quality open source projects and their major dependencies are probably another good source. also: "transformative fair use", not "stolen"

New comment by wskish in "What if we made advertising illegal?"

wskish — Sun, 06 Apr 2025 01:27:47 +0000

I think about this a lot. Consider the difference between the tidy signage of Tokyo versus the pell-mell streetfronts of Hong Hong. Societies should be able to choose how businesses impinge the public space.

New comment by wskish in "What if we made advertising illegal?"

wskish — Sun, 06 Apr 2025 01:19:55 +0000

Amplified messaging from corporations is not the same as the free speech of individuals. Just as we disallow advertising for cigarettes and hard liquor on TV, a democratic society should be free to select other classes of messages that corporations are not permitted to amplify into public spaces.

New comment by wskish in "Israeli Hetz 3 or US Navy SM-3 caught Iranian exoatmospheric threat"

wskish — Mon, 15 Apr 2024 04:57:21 +0000

"Let’s delve into the details"

New comment by wskish in "The Oregon Outback International Dark Sky Sanctuary"

wskish — Fri, 15 Mar 2024 03:23:31 +0000

To fully experience the night sky there is no substitute for getting up to altitude. Most of the atmosphere that really interferes with the view is way down low. Try a moonless night at 8000 to 11000 feet elevation in the eastern Sierra or Yosemite high country to really blow your mind. Boss level is a summit bivy during a new moon meteor shower with a close friend or lover.

New comment by wskish in "Architectural Issues in the Andrew Message System (1989) [pdf]"

wskish — Sat, 06 Jan 2024 04:02:06 +0000

"The Andrew Message System is one of the most ambitious and technically successful systems yet built in the area of electronic communication. In this paper, the authors of the system explain the key decisions in the architecture and reflect on what was done right and what was clearly wrong. Implementation details are mentioned only in passing, in order to maximize the relevance of this paper for the designers of successor systems."

Architectural Issues in the Andrew Message System (1989) [pdf]

wskish — Sat, 06 Jan 2024 04:02:06 +0000

Article URL: http://reports-archive.adm.cs.cmu.edu/anon/itc/CMU-ITC-076.pdf

Comments URL: https://news.ycombinator.com/item?id=38888274

Points: 2

# Comments: 1

New comment by wskish in "Hard disk LEDs and noisy machines"

wskish — Sat, 06 Jan 2024 03:32:22 +0000

I came here to mention MenuMeters as well. It's the closest thing I can find to those beloved X window system load indicators of yore.

New comment by wskish in "[dead]"

wskish — Wed, 20 Sep 2023 04:39:26 +0000

interesting, GPT refuses to summarize this content: "I'm sorry, but I can't generate a summary for that content." per https://github.com/jiggy-ai/hn_summary & https://t.me/hn_summary

New comment by wskish in "AI tests into top 1% for original creative thinking"

wskish — Sat, 08 Jul 2023 17:51:30 +0000

I'm curious about the methodology but couldn't find an associated paper or research report. The original source seem to be university PR.

New comment by wskish in "Time to subsidize e-bikes?"

wskish — Tue, 27 Jun 2023 03:41:04 +0000

It is amazing much room there is to re-optimize cities around smaller electric vehicle transportation when you think on a slightly longer timescale.

New comment by wskish in "The rule says, “No vehicles in the park”"

wskish — Sat, 24 Jun 2023 03:19:59 +0000

It isn't so clear to me. If it conveys a human in any way that humans don't naturally move unassisted then in my mind it qualifies as a conveyance and hence a vehicle, especially in the sense of the the French véhicule, from Latin vehiculum (“a carriage, conveyance”), from vehere (“to carry”)

New comment by wskish in "Show HN: DocsGPT-7B – purpose optimised and finetuned model for documentation QA"

wskish — Fri, 16 Jun 2023 14:43:08 +0000

"Attention with Linear Biases (ALiBi): Inherited from the MPT family, this feature eliminates the context length limits by replacing positional embeddings, allowing for efficient and effective processing of lengthy documents. In future we are planning to finish training on our larger dataset and to increase amount of tokens for context."

This is interesting, but also confusing. What is the current context limit? It mentions eliminating the limit but then mentions increasing it in the future.

New comment by wskish in "Native JSON Output from GPT-4"

wskish — Wed, 14 Jun 2023 20:48:18 +0000

here is code (with several examples) that takes it a couple steps further by validating the output json and pydantic model and providing feedback to the llm model when it gets either of those wrong:

https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas...

New comment by wskish in "SlimPajama: A 627B token cleaned and deduplicated version of RedPajama"

wskish — Sun, 11 Jun 2023 05:25:30 +0000

Do they mention anywhere the definition of "low quality" data or the proportion of removed data that was low quality versus duplicate?

They mention "When upsampled, we expect SlimPajama to perform equal to or better than RedPajama-1T when training at trillion token scale." But i guess "upsampling" in this case is just explicit duplication of the training data. So the only potential gains would be from the removal of the low quality data?

New comment by wskish in "GPT Best Practices"

wskish — Mon, 05 Jun 2023 19:31:58 +0000

Interesting that we have OpenAI using the more generic "GPT" here. Previously they would refer more specifically to ChatGPT, GPT-3, or GPT-4. I am guessing this is related to their trademark application for GPT, which was initially refused by the USPTO on the grounds of "GPT" being "merely descriptive".

https://news.ycombinator.com/item?id=36155583

New comment by wskish in "Initial USPTO response to OpenAI GPT trademark application"

wskish — Thu, 01 Jun 2023 18:52:51 +0000

I uploaded the USPTO office action to a JiggyBase (https://jiggy.ai) collection and used GPT-4 and the JiggyBase ChatGPT plugin to help make sense of this:

https://chat.openai.com/share/6a16cc77-4ef7-4e3a-bddb-dedd3f...

New comment by wskish in "Initial USPTO response to OpenAI GPT trademark application"

wskish — Thu, 01 Jun 2023 18:48:54 +0000

"REFUSAL—MERELY DESCRIPTIVE: Registration is refused because the applied-for mark merely describes a feature, function, or characteristic of applicant’s goods and services."

There are other details that exceed my trademark ken. Anyone with trademark experience care to parse this for us?

Initial USPTO response to OpenAI GPT trademark application

wskish — Thu, 01 Jun 2023 18:48:54 +0000

Article URL: https://tsdr.uspto.gov/documentviewer?caseId=sn97733259&docId=NFIN20230525093517#docIndex=0&page=1

Comments URL: https://news.ycombinator.com/item?id=36155583

Points: 3

# Comments: 3