Hacker News: rileyphone

New comment by rileyphone in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

rileyphone — Sat, 13 Jun 2026 05:01:25 +0000

All that says is some benchmarks aren’t worth the tokens it takes to evaluate them. Mythos is clearly capable of finding zero days other models can’t, and Fable is close enough to be lumped with it.

New comment by rileyphone in "Show HN: Prom.dev – Prompts that simulate Hacker News (and a tool to share them)"

rileyphone — Fri, 14 Nov 2025 00:02:19 +0000

Pretty neat! Really like the design and minimalism. Oh, and the free hosted models :-) (but I assume that's just for the demo). Kind of confused by the open in cursor button but otherwise clean.

It seems like there's a lot of stuff out there that's similar, but it's all either focused on art/roleplay on the one hand, or enterprise teams on the other. Most prompts I see are shared as raw text on twitter or something, to be lost in my bookmarks...

Anyways, here's a prompt. Next time I see an actually useful one out there I'll hopefully remember to save it on Prom.

https://prom.dev/p/where-is-mama

New comment by rileyphone in "An Efficient Implementation of SELF (1989) [pdf]"

rileyphone — Sun, 26 Oct 2025 00:02:16 +0000

Yes but it's really good for building better object systems, especially with newer features like proxies. In the SELF days they implemented Smalltalk with prototypes and found that it was faster than normal Smalltalk implementations.

https://www.researchgate.net/profile/Mario-Wolczko/publicati...

New comment by rileyphone in "Japan has opened its first osmotic power plant"

rileyphone — Wed, 27 Aug 2025 03:07:56 +0000

According to this delightful overview [1] of the desalination plant, the capacity overall is 12000kW so that's definitely close enough.

1. https://www.niph.go.jp/soshiki/suido/pdf/h21JPUS/abstract/r9...

New comment by rileyphone in "Ask HN: Who wants to be hired? (June 2025)"

rileyphone — Mon, 02 Jun 2025 17:53:45 +0000

Location: Seattle, WA

Remote: Sure

Willing to relocate: No

Technologies: Javascript (Node/Web/Bun), Linux, Python, SQL (SQL Server/MySQL/Postgres/Sqlite), Azure, k8s/docker, React, Typescript, and many more

Resume: https://rileystew.art/files/resume.pdf

Email: me @ the above domain

Website: https://rileystew.art/

I'm a generalist with a focus on backend and infrastructure -- in my career that's meant a lot of diving into logs, probing systems, and solving distributed bugs. In my own time I am working on an object-oriented Javascript framework and a custom autoencoder for visualizing latent states of LLMs. Looking for the opportunity to build something great and solve interesting problems.

New comment by rileyphone in "Evolving OpenAI's Structure"

rileyphone — Mon, 05 May 2025 19:52:48 +0000

From talking to people, the average user relies on memories and chat history, which is not easy to migrate. I imagine that's the part of the strategy to keep people from hopping model providers.

New comment by rileyphone in "Design for 3D-Printing"

rileyphone — Mon, 05 May 2025 16:01:24 +0000

I got a Sovol SV06 ACE a few months ago as it seemed to have most of the nice features of the Bambu (like auto bed leveling) without the closedness. The printer runs Klipper and you can ssh into it. So far there's been one issue where I had to replace a fan but otherwise it's been great. Much cheaper than a new Prusa too.

New comment by rileyphone in "Ask HN: Who is hiring? (April 2025)"

rileyphone — Thu, 03 Apr 2025 19:27:44 +0000

Page for the role doesn't have Seattle, only SF.

New comment by rileyphone in "Stoop Coffee: A simple idea transformed my neighborhood"

rileyphone — Wed, 26 Mar 2025 17:17:51 +0000

It's baked in to the process as part of design review, after getting pass the first wall of zoning.

https://www.seattle.gov/neighborhoods/public-participation/e...

New comment by rileyphone in "DOJ will push Google to sell off Chrome"

rileyphone — Tue, 19 Nov 2024 18:26:27 +0000

Firefox has made Mozilla billions over its lifetime by selling the default search engine rights to Yahoo and Google. Chrome, having a much greater user base, would demand a correspondingly higher fee (probably around $10b a year). Now, the other problem is there is no other search engine to compete with Google at that level, but that might change with independence of Chrome.

New comment by rileyphone in "We're in the brute force phase of AI – once it ends, demand for GPUs will too"

rileyphone — Tue, 10 Sep 2024 15:54:37 +0000

If you spend 1000W on 1 gigaflops, but could have gotten 1 teraflops instead on newer hardware, you are mostly just throwing money away. Unless fab capacity is severely limited in the future or energy becomes too cheap to meter, the opportunity cost is just too great for your statement to be true.

New comment by rileyphone in "Ask HN: What are some "toy" projects you used to learn neural networks hands-on?"

rileyphone — Mon, 12 Aug 2024 18:56:30 +0000

Been working on an autoencoder that converts the hidden states of transformer models into a spatial representation that can be visualized. Started more on the toy scale but now I'm trying to scale it beyond my humble 3060. Using LLMs to help with torch and such but they are limited in the details of tensor twiddling.

https://github.com/ristew/weightscan

New comment by rileyphone in "Codestral Mamba"

rileyphone — Wed, 17 Jul 2024 07:38:38 +0000

Gemini is probably using ring attention. But scaling to that size requires more engineering effort in terms of interlink that goes beyond the purpose of this release from Mistral.

New comment by rileyphone in "Newswire: A large-scale structured database of a century of historical news"

rileyphone — Mon, 01 Jul 2024 01:52:46 +0000

According to the paper, the dataset goes up to 1978 because that's when copyright law was updated to automatically apply to newswires. It's unfortunate that we got into the situation where academia has to play by the rules wrt copyright while big private labs flaunt it.

New comment by rileyphone in "Uncensor any LLM with abliteration"

rileyphone — Thu, 13 Jun 2024 06:40:46 +0000

In that case there are two attractors - one towards the Golden Gate Bridge and one towards the harmless, helpful, honest assistant persona. Techniques as such probably get weirder results with model scale but no reason to think they get wiped out.

New comment by rileyphone in "OpenAI Welcomes Sarah Friar (CFO) and Kevin Weil (CPO)"

rileyphone — Mon, 10 Jun 2024 18:30:43 +0000

In this case Azure is responsible for the datacenters, billing, and support.

New comment by rileyphone in "Go east from Seattle"

rileyphone — Mon, 03 Jun 2024 19:01:05 +0000

There's also the oceanic currents carrying warm water from the gulf. Europe is in a very lucky position.

New comment by rileyphone in "D-Expressions: Lisp power, Dylan style [pdf]"

rileyphone — Wed, 22 May 2024 05:51:59 +0000

Unary operators are still operators. The integer parsing rules are probably different. In Lisp, -x would be a symbol, and the proper analog to -123 would be (- x) eg.

New comment by rileyphone in "D-Expressions: Lisp power, Dylan style [pdf]"

rileyphone — Mon, 20 May 2024 18:37:03 +0000

Not really because the ordering is unambiguous given the parens. No need for operator precedence rules like PEMDAS.

New comment by rileyphone in "Meta Llama 3"

rileyphone — Thu, 18 Apr 2024 16:55:05 +0000

The bigger size is probably from the bigger vocabulary in the tokenizer. But most people are running this model quantized at least to 8 bits, and still reasonably down to 3-4 bpw.