Hacker News: solresol

New comment by solresol in "Anthropic officially bans using subscription auth for third party use"

solresol — Thu, 19 Feb 2026 03:48:50 +0000

I got banned for violating terms of use apparently, but I'm mystified as to what I rule I broke, and appealing just vanishes into the ether.

New comment by solresol in "We're all called Julia, or maybe ChatGPT calls itself Julia"

solresol — Wed, 11 Feb 2026 04:12:05 +0000

Has anyone else got examples of reasoning traces where it uses a word in a way that no human being would?

We're all called Julia, or maybe ChatGPT calls itself Julia

solresol — Wed, 11 Feb 2026 04:12:05 +0000

Article URL: https://solresol.substack.com/p/were-all-called-julia-or-maybe-chatgpt

Comments URL: https://news.ycombinator.com/item?id=46970734

Points: 3

# Comments: 1

New comment by solresol in "Ask HN: What are you working on? (February 2026)"

solresol — Sun, 08 Feb 2026 23:48:22 +0000

I just proved that constraint solving problems can be encoded as p-adic linear regression problems[+], and that therefore we can use machine learning optimisation techniques to get exact answers.

So of course no journal or conference is in the least bit interested, and I'm now reformatting it for another obscure low-tier journal that no-one will ever read.

Otherwise:

- automating the translation of a Byzantine Greek work that has never been translated into English before. https://stephanos.symmachus.org

- also preparing evidence for a case against the university I sometimes work for.

[+] Linear regression, but instead of minimising the Euclidean distance, minimise the p-adic distance - https://en.wikipedia.org/wiki/P-adic_valuation

New comment by solresol in "Ask HN: What are you working on? (January 2026)"

solresol — Mon, 12 Jan 2026 02:50:59 +0000

Stephanos of Byzantium wrote what we would call an encyclopedia of people and places. Most of it has been lost, but shortened versions still exist. I've set up a bot to scan a version of what we have, translate it, extract out the proper nouns and try to figure out what was lost. https://stephanos.symmachus.org/ I'm also linking it to the translation of Pausanias https://pausanias.symmachus.org that another bot is doing.

Also, trying to finish a PhD on machine learning when you want to minimise a p-adic loss.

New comment by solresol in "Ask HN: How are you sandboxing coding agents?"

solresol — Sat, 27 Dec 2025 13:11:03 +0000

I create a separate Linux user (which doesn't have sudo rights) for each project. I have to log each user in to Claude code or codex, but then I can use ordinary Unix permissions to keep the bots under control and isolated.

New comment by solresol in "Largest cargo sailboat completes first Atlantic crossing"

solresol — Sun, 09 Nov 2025 06:16:50 +0000

> The volume of cargo carried by sailing vessels in the old days was orders of magnitude lower.

Surprisingly, no, it wasn't. I'll slightly fudge the numbers and talk in terms of proportion of world trade that was carried by ocean-going vessels (because if you double the population then it's reasonable to talk about doubling the number of ships).

The world economy was very globalised in 1913. That level of globalisation in trade wasn't matched again until the 1990s.

We're only a little more global now than we were in the age of sail.

The British navy and merchant fleet was a wonder of its era.

It's 2025 – Narrative Learning is the new baseline to beat for explainable ML

solresol — Fri, 17 Oct 2025 11:39:20 +0000

Article URL: https://arxiv.org/abs/2510.09723

Comments URL: https://news.ycombinator.com/item?id=45615530

Points: 1

# Comments: 0

New comment by solresol in "Ask HN: What are you working on? (October 2025)"

solresol — Mon, 13 Oct 2025 03:57:56 +0000

Writing a course for a customer on how to use Claude Code well, especially around brownfield development (working on existing code bases, not so much around vibe-coding something new).

New comment by solresol in "BYD builds fastest car"

solresol — Mon, 06 Oct 2025 04:19:27 +0000

If the "outcompeting" is possible because of Chinese government subsidies, then it's important to protect local industry from unfair competition.

It's similar to the logic behind anti-trust actions against monopolists. If the playing field isn't level, then the USA government steps in to level it.

(Whether BYD is subsidised or not is another question, but the above is the logic of protecting local industry.)

New comment by solresol in "Galileo’s telescopes: Seeing is believing (2010)"

solresol — Wed, 13 Aug 2025 05:37:08 +0000

Indeed. The obvious counter-example to the claim is "rainbows" which were definitely the topic of heated scientific argument for hundreds of years (and non-scientific ones before that).

New comment by solresol in "Fine-tuning LLMs is a waste of time"

solresol — Wed, 11 Jun 2025 00:05:28 +0000

I think of it as trying to encourage the LLM to want to give answers from a particular part of the phase space. You can do it by fine tuning it to be more likely to return values from there, or you can prompt it to get into that part of the phase space. Either works, but fiddling around with prompts doesn't require all that much MLops or compute power.

That said, fine tuning small models because you have to power through vast amounts of data where a larger model might be cost ineffective -- that's completely sensible, and not really mentioned in the article.

Elder care and AI agents via accounting and software development

solresol — Wed, 11 Jun 2025 00:01:14 +0000

Article URL: https://solresol.substack.com/p/elder-care-and-ai-agents-via-accounting

Comments URL: https://news.ycombinator.com/item?id=44242853

Points: 1

# Comments: 0

New comment by solresol in "Trying to teach in the age of the AI homework machine"

solresol — Mon, 26 May 2025 21:23:04 +0000

I have been wrestling with this too. I only see two options: no tech university or AI wrangling university.

https://solresol.substack.com/p/you-can-no-longer-set-an-und...

New comment by solresol in "Ask HN: What are you working on? (May 2025)"

solresol — Mon, 26 May 2025 13:26:48 +0000

A beautiful implementation of the most exotic sorting algorithm I'm going to teach this semester:

https://bead-sort.arithmetic.guru/

Oh, and also a PhD on p-adic machine learning, but no one will remember that.

The answer to the million dollar question is 2031

solresol — Fri, 23 May 2025 03:29:02 +0000

Article URL: https://solresol.substack.com/p/the-answer-to-the-million-dollar

Comments URL: https://news.ycombinator.com/item?id=44069609

Points: 2

# Comments: 0

New comment by solresol in "A Research Preview of Codex"

solresol — Sat, 17 May 2025 06:38:51 +0000

I'm not sure what's wrong with me, but I just wasted several hours wrestling codex to make it behave.

Here's my workflow that keeps failing: - it writes some code. It looks good a first glance - I push it to github - automated tests on github show that there's a problem - go back to codex and ask it to fix it - it does stuff. It looks good again.

Now what do I do? If I ask it to push again to github, then it will often create a pull request that doesn't include stuff from the first pull request, but it's not a pull request that stacks on top of the previous pull request, it's a pull request that stacks on top of main.

When asked to write something that called out to gpt-4.1-mini, it used openai.ChatCompletion.create (!?!!?)

I just found myself using claude to fix codex's mistakes.

New comment by solresol in "Ask HN: What are you working on? (April 2025)"

solresol — Mon, 28 Apr 2025 05:40:41 +0000

Trying to measure how well LLMs can make scientific hypotheses, and more generally, execute on the scientific process (as part of a pivot in my PhD).

New comment by solresol in "Reproducibility project fails to validate dozens of biomedical studies"

solresol — Sat, 26 Apr 2025 13:24:51 +0000

At the time when they need to be making connections and needing patronage you want PhD students to be showing up integrity and honesty problems and asking awkward questions about the powerful people in the community?

Of course that's what should be happening, but the incentives aren't pushing in the right direction for it currently.

New comment by solresol in "Show HN: I made a free tool that analyzes SEC filings and posts detailed reports"

solresol — Mon, 14 Apr 2025 05:08:24 +0000

It seems to be the season for scraping SEC filing archives and running them through AI bots to extract information. I made this:

https://boards.industrial-linguistics.com/

It only looks at information about directors on company boards, and unlike your much better project, I don't have any clear idea how to commercialise it.