Hacker News: physicsgraph

Cargo Cult Bureaucracy

physicsgraph — Fri, 08 May 2026 12:38:47 +0000

Article URL: https://graphthinking.blogspot.com/2026/05/cargo-cult-bureaucracy.html

Comments URL: https://news.ycombinator.com/item?id=48062200

Points: 2

# Comments: 0

The persistent need for general knowledge and subject-matter expertise with LLMs

physicsgraph — Tue, 16 Dec 2025 21:13:46 +0000

Article URL: https://graphthinking.blogspot.com/2025/12/the-persistent-need-for-general.html

Comments URL: https://news.ycombinator.com/item?id=46294558

Points: 1

# Comments: 0

Website unresponsive: diagnostic steps and blocking the AI crawlers

physicsgraph — Thu, 04 Dec 2025 11:43:06 +0000

Article URL: https://physicsderivationgraph.blogspot.com/2025/12/website-unresponsive-diagnostic-steps.html

Comments URL: https://news.ycombinator.com/item?id=46146499

Points: 2

# Comments: 2

Unspoken Currency of Office Politics: Leverage and Sanction Between Coworkers

physicsgraph — Sat, 17 May 2025 21:22:08 +0000

Article URL: https://graphthinking.blogspot.com/2025/05/leverage-and-sanction-between-coworkers.html

Comments URL: https://news.ycombinator.com/item?id=44017056

Points: 88

# Comments: 16

US NSA Director Timothy Haugh Fired

physicsgraph — Fri, 04 Apr 2025 11:45:11 +0000

Article URL: https://www.reuters.com/world/us/us-nsa-director-timothy-haugh-fired-washington-post-reports-2025-04-04/

Comments URL: https://news.ycombinator.com/item?id=43580850

Points: 7

# Comments: 0

New comment by physicsgraph in "I am rich and have no idea what to do"

physicsgraph — Thu, 02 Jan 2025 23:16:25 +0000

Find something that other people would see as infeasible or inaccessible and work on that. You are in a position of privilege that can be used to advance well-being and knowledge.

Deciding whether to explore challenges solo versus as part of a team is a crucial differentiator.

New comment by physicsgraph in "Understanding how bureaucracy develops"

physicsgraph — Sat, 19 Oct 2024 23:55:50 +0000

To summarize the main two take-aways, measure ROI (return on investment) and be Agile.

New comment by physicsgraph in "Ask HN: Where I can find great blogs?"

physicsgraph — Mon, 02 Sep 2024 12:15:46 +0000

Have you searched through https://hn.algolia.com/?q=ask+hn+blogs ?

Founder Mode and Dunbar's Number

physicsgraph — Mon, 02 Sep 2024 12:14:00 +0000

Article URL: https://graphthinking.blogspot.com/2024/09/founder-mode-and-dunbars-number.html

Comments URL: https://news.ycombinator.com/item?id=41424792

Points: 1

# Comments: 0

New comment by physicsgraph in "Open-Source Fault Tree Analysis (OSFTA)"

physicsgraph — Fri, 03 May 2024 17:27:44 +0000

Sounds interesting, but the github repo doesn't seem to have enough README content to explain who should use the project or how to use the project.

New comment by physicsgraph in "The "missing" graph datatype already exists. It was invented in the '70s"

physicsgraph — Tue, 05 Mar 2024 20:50:35 +0000

The original blob post [0] referenced hypergraphs and other more complicated structures like property graphs.

[0] https://news.ycombinator.com/item?id=39592444

New comment by physicsgraph in "The "missing" graph datatype already exists. It was invented in the '70s"

physicsgraph — Tue, 05 Mar 2024 20:47:04 +0000

The back-and-forth exchange between blogs, each with comment threads on HN, is a great use of the Internet.

Augmenting a containerized large language model with text files for context

physicsgraph — Tue, 26 Dec 2023 08:04:43 +0000

Article URL: https://graphthinking.blogspot.com/2023/12/augmenting-containerized-large-language.html

Comments URL: https://news.ycombinator.com/item?id=38769754

Points: 1

# Comments: 0

New comment by physicsgraph in "Small offline large language model – TinyChatEngine from MIT"

physicsgraph — Mon, 18 Dec 2023 12:08:24 +0000

Thanks for the suggestion. I'm new to running LLMs so I'll take a look at your suggestion [0]. My ~10 year old MacBook Air has 4GB of RAM, so I'm primarily interested in smaller LLMs.

[0] https://github.com/ggerganov/llama.cpp

New comment by physicsgraph in "Small offline large language model – TinyChatEngine from MIT"

physicsgraph — Mon, 18 Dec 2023 12:05:01 +0000

Your assessment is exactly correct -- the blog post is my note-to-self about getting the repo to work. My "added value" in the post is a Dockerfile for ease of installation.

Small offline large language model – TinyChatEngine from MIT

physicsgraph — Mon, 18 Dec 2023 02:57:28 +0000

Article URL: https://graphthinking.blogspot.com/2023/12/small-offline-large-language-model.html

Comments URL: https://news.ycombinator.com/item?id=38678773

Points: 117

# Comments: 24

New comment by physicsgraph in "How to Make the Most of 1-on-1 Meetings"

physicsgraph — Tue, 01 Aug 2023 10:48:18 +0000

The premise towards 1-on-1s that "regular 1-on-1 meetings often feel like a burden and overhead" indicates the value of 1-on-1s isn't clear to the author. The 1-on-1s are an opportunity for supervisors to learn about the long-term goals of their employees.

The author's content presents short-term oriented assessment more appropriate for team syncs.

I've collected questions to ask in 1-on-1s here [0].

[0] https://graphthinking.blogspot.com/2022/10/one-on-one-questi...

Matrixed organizations: best practices and risks for team members

physicsgraph — Tue, 01 Aug 2023 10:43:38 +0000

Article URL: https://graphthinking.blogspot.com/2023/07/matrixed-organizations-best-practices.html

Comments URL: https://news.ycombinator.com/item?id=36954477

Points: 1

# Comments: 0

New comment by physicsgraph in "The Pile: An 800GB Dataset of Diverse Text for Language Modeling"

physicsgraph — Mon, 12 Jun 2023 01:14:12 +0000

Previous post: https://news.ycombinator.com/item?id=25607809

New comment by physicsgraph in "Improving mathematical reasoning with process supervision"

physicsgraph — Thu, 01 Jun 2023 02:51:07 +0000

The training data used [0] is written using "leaps of logic" which provide context for how the solution was derived. There isn't sufficient detail in the training data to formally check each step using a Computer Algebra System [1]. Therefore, whether or not any output from the OpenAI software is actually correct is left as an exercise for the user. Answering "Was the hallucination correct?" involves manually checking each step.

This advancement is good, but it's limited by the precision of the training data.

[0] https://artofproblemsolving.com/wiki/index.php/2015_AIME_II_...

[1] https://en.wikipedia.org/wiki/Computer_algebra_system