Hacker News: theodorewiles

New comment by theodorewiles in "Claude Fable 5"

theodorewiles — Wed, 10 Jun 2026 02:35:15 +0000

... and /compact triggers

Error: Error during compaction: API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup).

Guys please be serious

New comment by theodorewiles in "Claude Fable 5"

theodorewiles — Tue, 09 Jun 2026 22:05:30 +0000

AI psychosis

New comment by theodorewiles in "Claude Fable 5"

theodorewiles — Tue, 09 Jun 2026 21:00:53 +0000

Here's a song it wrote for me (suno arranged). Not sure if it's AI psychosis but scary good IMO.

https://suno.com/s/98uSGabHN42G3YHc

New comment by theodorewiles in "All of human cooking compressed into 2 megabytes"

theodorewiles — Wed, 27 May 2026 22:05:06 +0000

I haven't but looks cool!

New comment by theodorewiles in "All of human cooking compressed into 2 megabytes"

theodorewiles — Wed, 27 May 2026 18:16:46 +0000

yeah I took a look at this and others and tried to pull together some helpful 'flavor maps':

https://transcendent-choux-d1b930.netlify.app/

New comment by theodorewiles in "The current AI pricing was always going to go away"

theodorewiles — Fri, 22 May 2026 16:48:52 +0000

Commoditize your complement - I expect to see this most in consumer AI (after that starts actually working...)

It will be important for Apple to have good enough, cheap local LLM models that run on-device.

If the barrier to performance shifts from fundamental model capability to context collection and management I would expect to see folks focused on that problem continuing to drive open-weight LLM model development in some shape or form.

New comment by theodorewiles in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

theodorewiles — Thu, 21 May 2026 17:04:20 +0000

My take is that B2C AI applications are kind of structurally limited by how hard it is to build personalized context.

The idea of capable local models could be a huge unlock here if they are able to do the bottom-up context collection research / tagging / etc. at scale.

New comment by theodorewiles in "Claude Code Routines"

theodorewiles — Tue, 14 Apr 2026 18:08:19 +0000

How does this deal with stop hooks? Can it run https://github.com/anthropics/claude-code/blob/main/plugins/...

New comment by theodorewiles in "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"

theodorewiles — Tue, 17 Mar 2026 23:07:14 +0000

I think the research / plan / execute idea is good but feels like you would be outsourcing your thinking. Gotta review the plan and spend your own thinking tokens!

New comment by theodorewiles in "Searching for the Agentic IDE"

theodorewiles — Wed, 11 Mar 2026 19:01:03 +0000

Yeah I vibe coded a simple app that takes an org-mode file, renders it as a kanban board, and lets me spin up agents for each task with the prompt in the body in a named tmux session. The frontend gets updated via Claude code hooks when an agent is idle.

I think the key is to combine human and agent task tracking in one pane of glass.

New comment by theodorewiles in "Agents.md file isn't the problem. Your lack of Evals is"

theodorewiles — Wed, 25 Feb 2026 12:47:36 +0000

Ai;dr

New comment by theodorewiles in "Claude Code On-the-Go"

theodorewiles — Sun, 04 Jan 2026 21:37:44 +0000

I have been doing the same but with happy. It works quite well for quick brainstorms etc. but for deeper work on a real research / plan / implement thing I think you need to actually engage with the output which is hard to do on mobile. Maybe if I had a better UI than terminus to read and check the remote files I would be able to get more done.

I am also hoping / trying to put Claude code on top of a personal zettlekasten to automate more of my “personal life” tasks and get more stuff done for me. Haven’t gotten it really singing yet but I think that could also be really cool.

New comment by theodorewiles in "Haiku Validator"

theodorewiles — Mon, 29 Sep 2025 16:35:47 +0000

Cool idea. Note that sometimes syllables depend on context. So syllable count I think needs to be a range.

Blessed vs “bless-ed” for example

Camera can be said cam-ra or cam-er-a for example.

Perplexity launches revenue share with content publishers (updated)

theodorewiles — Mon, 25 Aug 2025 19:33:03 +0000

Article URL: https://www.wsj.com/business/media/perplexity-ai-search-publisher-revenue-507987

Comments URL: https://news.ycombinator.com/item?id=45017968

Points: 2

# Comments: 0

Perplexity launches revenue share with content publishers

theodorewiles — Mon, 25 Aug 2025 18:52:05 +0000

Article URL: https://www.perplexity.ai/hub/blog/introducing-the-perplexity-publishers-program

Comments URL: https://news.ycombinator.com/item?id=45017519

Points: 2

# Comments: 2

New comment by theodorewiles in "Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker"

theodorewiles — Tue, 29 Jul 2025 18:40:23 +0000

yes

New comment by theodorewiles in "Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker"

theodorewiles — Tue, 29 Jul 2025 17:54:47 +0000

Please shoot me a note - I'm trying to figure this out for my enterprise now, would love to figure out a way to get you in / trial it out.

New comment by theodorewiles in "Study mode"

theodorewiles — Tue, 29 Jul 2025 17:39:52 +0000

https://www.nature.com/articles/s41598-025-97652-6

This isn't study mode, it's a different AI tutor, but:

"The median learning gains for students, relative to the pre-test baseline (M = 2.75, N = 316), in the AI-tutored group were over double those for students in the in-class active learning group."

New comment by theodorewiles in "Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker"

theodorewiles — Tue, 29 Jul 2025 16:56:27 +0000

Looks really cool - I noticed Enterprise has smart consent management?

The thing I think some enterprise customers are worried about in this space is that in many jurisdictions you legally need to disclose recording - having a bot join the call can do that disclosure - but users hate the bot and it takes up too much visibility on many of these calls.

Would love to learn more about your approach there

New comment by theodorewiles in "AccountingBench: Evaluating LLMs on real long-horizon business tasks"

theodorewiles — Mon, 21 Jul 2025 23:26:59 +0000

For me this benchmark suggests that an LLM will try to “force the issue” which results in compounding errors. But I think the logical counterpoint is that you may be asking the LLM to come up an answer without all of the necessary details? Some of these are “baked into” historical transactions which is why it does well in months 1-2.

My takeaway is scaling in the enterprise is about making implicit information explicit.