Viewing profile — solresol
solresol
HN member- Joined
- Sun, Oct 04, 2015, 8:04 AM UTC
- HN karma
- 748
- Public activity
- 244 items
- HN profile
- View on Hacker News ↗
About solresol
Recent public activity
-
comment
Comment #48782896
In some fields, all of those statements are true already. In a large number of few fields, all of those statements will be true in the near future (10 years maximum). There's no re…
-
comment
Comment #47069667
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.
-
comment
Comment #46970735
Has anyone else got examples of reasoning traces where it uses a word in a way that no human being would?
- story
-
comment
Comment #46939827
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…
-
comment
Comment #46583408
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 vers…
-
comment
Comment #46401603
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 t…
-
comment
Comment #45863383
> 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 pr…
- story
-
comment
Comment #45564544
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 n…
-
comment
Comment #45487608
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 a…
-
comment
Comment #44884960
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 t…
-
comment
Comment #44242879
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 f…
- story
-
comment
Comment #44101817
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...
-
comment
Comment #44097243
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, …
- story
-
comment
Comment #44012451
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 …
-
comment
Comment #43817969
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).
-
comment
Comment #43803416
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 t…
-
comment
Comment #43678252
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 …
-
comment
Comment #43357827
(Australia) I received my notice from the land valuer general yesterday (for unimproved land value). Looking at building costs for my area and what other houses are going for in th…
-
comment
Comment #43054358
I tried... it started with the idea was that log loss might not be the best option for training, and maybe it should be a loss related to how wrong the predicted word was. Predicti…
-
comment
Comment #42746158
When I last looked up the literature, Keto diet was one of the least effective interventions. That is, if you follow it, I'm sure it works. But the vast majority of people drop out…
-
comment
Comment #42669743
I administered the CDT to ChatGPT and got Claude to diagnose what was wrong with the "patient" based on the results. There are signs of pre-frontal cortex damage or early stage dem…