Hacker News: oli5679

Freedom of Information Request – Chat GPT Conversations – UK Science Secretary

oli5679 — Mon, 20 Apr 2026 18:33:04 +0000

Article URL: https://www.gov.uk/government/publications/foi2025-00120-plain-text-copy-of-peter-kyles-chatgpt-history/response-plain-text-copy-of-peter-kyles-chatgpt-history

Comments URL: https://news.ycombinator.com/item?id=47838626

Points: 1

# Comments: 0

Ghostty – Terminal Emulator

oli5679 — Sun, 01 Mar 2026 12:13:03 +0000

Article URL: https://ghostty.org/docs

Comments URL: https://news.ycombinator.com/item?id=47206009

Points: 863

# Comments: 359

New comment by oli5679 in "How to code Claude Code in 200 lines of code"

oli5679 — Thu, 08 Jan 2026 21:22:43 +0000

https://github.com/mistralai/mistral-vibe

This is a really nice open source coding agent implementation. The use of async is interesting.

Nicolas Maduro – US Bounty

oli5679 — Sat, 03 Jan 2026 14:00:41 +0000

Article URL: https://www.state.gov/nicolas-maduro-moros

Comments URL: https://news.ycombinator.com/item?id=46476716

Points: 1

# Comments: 0

Open AI Europe terms of use

oli5679 — Mon, 22 Dec 2025 22:11:07 +0000

Article URL: https://openai.com/en-GB/policies/eu-terms-of-use/

Comments URL: https://news.ycombinator.com/item?id=46359761

Points: 1

# Comments: 0

Code for mistral vibe – Mistral's open-source CLI coding assistant

oli5679 — Sun, 14 Dec 2025 12:29:46 +0000

Article URL: https://github.com/mistralai/mistral-vibe

Comments URL: https://news.ycombinator.com/item?id=46262574

Points: 2

# Comments: 0

New comment by oli5679 in "Weight-sparse transformers have interpretable circuits [pdf]"

oli5679 — Sat, 22 Nov 2025 13:53:55 +0000

This ties directly into the superposition theory.

It is believed dense models cram many features into shared weights, making circuits hard to interpret.

Sparsity reduces that pressure by giving features more isolated space, so individual neurons are more likely to represent a single, interpretable concept.

Install script does rm -RF /usr for Ubuntu

oli5679 — Mon, 03 Nov 2025 18:30:42 +0000

Article URL: https://github.com/MrMEEE/bumblebee-Old-and-abbandoned/issues/123

Comments URL: https://news.ycombinator.com/item?id=45802497

Points: 2

# Comments: 0

New comment by oli5679 in "The case for the return of fine-tuning"

oli5679 — Sun, 19 Oct 2025 11:01:05 +0000

The OpenAI fine-tuning api is pretty good - you need to label an evaluation benchmark anyway to systematically iterate on prompts and context, and it’s often creates good results if you give it a 50-100 examples, either beating frontier models or allowing a far cheaper and faster model to catch up.

It requires no local gpus, just creating a json and posting to OpenAI

https://platform.openai.com/docs/guides/model-optimization

New comment by oli5679 in "One-man campaign ravages EU 'Chat Control' bill"

oli5679 — Wed, 08 Oct 2025 19:40:33 +0000

One interesting anecdote about this bill was that the European Commission allegedly funded digital advertisements promoting it, targeting specific political demographics, which is something that could possibly be prohibited by their own regulations.

https://noyb.eu/en/noyb-files-complaint-against-eu-commissio...

https://eur-lex.europa.eu/EN/legal-content/summary/transpare...

Self-Replicating NPM Package Supply Chain Worm 'Shai Hulud'

oli5679 — Sat, 20 Sep 2025 18:40:01 +0000

Article URL: https://www.aikido.dev/blog/s1ngularity-nx-attackers-strike-again

Comments URL: https://news.ycombinator.com/item?id=45316053

Points: 2

# Comments: 0

New comment by oli5679 in "Are we decentralized yet?"

oli5679 — Sun, 31 Aug 2025 14:55:23 +0000

HHI is a pretty interesting metric. It’s calculated by taking each firm’s market share, squaring it, and summing across all firms.

This gives the probability that two randomly chosen customers belong to the same firm.

In one micro models of oligopoly, Cournot competition, it lines up directly with the markup firms can sustain.

Outside of theory, it’s an intuitive way to average together the market power of all firms, with increases in market share for bigger players being weighted more heavily.

New comment by oli5679 in "Knuth on ChatGPT (2023)"

oli5679 — Sat, 09 Aug 2025 19:35:29 +0000

Here is gpt 5 thinking posting all 20 questions verbatim. Appreciate I might get better results one question at a time.

https://chatgpt.com/share/6897a21b-25c0-8011-a10a-85850870da...

Pretty interesting - some contamination, some better answers, and it failed to write a sentence with all 5-letter-words. I’d have expected it to pass this one!

Simple example: “Every night, dreams swirl swiftly.

Tom Lehrer, RIP

oli5679 — Sun, 27 Jul 2025 21:53:48 +0000

Article URL: https://marginalrevolution.com/marginalrevolution/2025/07/tom-lehrer-rip.html

Comments URL: https://news.ycombinator.com/item?id=44705070

Points: 6

# Comments: 1

Anthropic hires back Claude code creators, 2 weeks after joining cursor

oli5679 — Wed, 16 Jul 2025 21:07:39 +0000

Article URL: https://medial.app/news/anthropic-hired-back-two-of-its-employees-just-two-weeks-after-they-left-for-a-competitor-a5f1ee0dea6e5

Comments URL: https://news.ycombinator.com/item?id=44586786

Points: 4

# Comments: 0

The Mystery of Richard Posner

oli5679 — Sat, 28 Jun 2025 14:32:10 +0000

Article URL: https://lawliberty.org/features/the-mystery-of-richard-posner/

Comments URL: https://news.ycombinator.com/item?id=44404983

Points: 3

# Comments: 1

Guideline for New Roles

oli5679 — Sun, 22 Jun 2025 19:33:56 +0000

Article URL: https://grahamhelton.com/notes/role_guidelines

Comments URL: https://news.ycombinator.com/item?id=44349630

Points: 1

# Comments: 0

Good Writing

oli5679 — Sat, 24 May 2025 15:03:37 +0000

Article URL: https://paulgraham.com/goodwriting.html

Comments URL: https://news.ycombinator.com/item?id=44081586

Points: 306

# Comments: 310

New comment by oli5679 in "In 2025, venture capital can't pretend everything is fine any more"

oli5679 — Sun, 11 May 2025 14:31:25 +0000

It’s really easy to be cynical.

There is a big upside potential for high growth companies taking advantage of technology trends.

Today, Google’s revenue is £263.66 Billion. This is nearly 300x the revenue Google generated in 2003 ($961.9 million). The company went public on August 19, 2004, at $85 per share, valuing the company at $23 billion. After the IPO, Google reported $1.47 billion in revenue for fiscal year 2003, with a profit of $105.6 million.

New comment by oli5679 in "OpenAI says it has evidence DeepSeek used its model to train competitor"

oli5679 — Thu, 30 Jan 2025 15:17:21 +0000

this is pretty ridiculous

A. below is a list of OpenAI initial hires from Google. It's implausible to me that there wasn't quite significant transfer of Google IP

B. google published extensively, including the famous 'attention is all you need' paper, but open-ai despite its name, has not explained the breakthroughs that enabled O1. It has also switched from a charity to a for-profit company.

C. Now this company, with a group of smart, unknown machine learning engineers, presumably paid fractions of what OpenAI are published, has created a model far cheaper, and openly published the weights, many methodological insights, which will be used by OpenAI.

1. Ilya Sutskever – One of OpenAI’s co-founders and its former Chief Scientist. He previously worked at Google Brain, where he contributed to the development of deep learning models, including TensorFlow. 2. Jakub Pachocki – Formerly OpenAI’s Director of Research, he played a major role in the development of GPT-4. He had a background in AI research that overlapped with Google’s fields of interest. 3. John Schulman – Co-founder of OpenAI, he worked on reinforcement learning and helped develop Proximal Policy Optimization (PPO), a method used in training AI models. While not a direct Google hire, his work aligned with DeepMind’s research areas. 4. Jeffrey Wu – One of the key researchers involved in fine-tuning OpenAI’s models. He worked on reinforcement learning techniques similar to those developed at DeepMind. 5. Girish Sastry – Previously involved in OpenAI’s safety and alignment work, he had research experience that overlapped with Google’s AI safety initiatives.