Hacker News: jjfoooo4

New comment by jjfoooo4 in "Private equity bought America's essential services"

jjfoooo4 — Thu, 28 May 2026 14:23:07 +0000

Down from 10 years ago, down quite a bit from 20 years ago

New comment by jjfoooo4 in "Magnifica Humanitas"

jjfoooo4 — Tue, 26 May 2026 14:30:00 +0000

But there's not an everyday use case for firearms and explosives for the average person. There's civilian, everyday task that would be easier were better firearms and explosives available

New comment by jjfoooo4 in "The main thing about P2P meth is that there's so much of it (2021)"

jjfoooo4 — Sat, 16 May 2026 21:47:42 +0000

Surely both manufacturer and convenience store have incentive to push the addictive product in this scenario.

In any case, drug dealers really don’t need to do any pushing, the drugs sell themselves. Have you ever taken an opioid? The idea that unfettered access would result in less addiction and death is a pretty remarkable POV

New comment by jjfoooo4 in "Apple reports second quarter results"

jjfoooo4 — Fri, 01 May 2026 01:52:35 +0000

That they aren’t participating in the AI arms race is very good for current earning

New comment by jjfoooo4 in "UAE to leave OPEC"

jjfoooo4 — Tue, 28 Apr 2026 22:17:45 +0000

> Of course, this then introduces the circular reasoning "because of a potential US attack", but of course if Iran wasn't funding Hamas, Hezbollah, Houthis

I think the first step of thinking about war objectively is to consider how each side sees it. The US POV is no less circular, from Iran’s perspective - they could list any number of provocations from the US to justify arming themselves, none more obvious than the war itself.

The debate around who started the hostility is ultimately pointless, the question is what to do about. Ideally the answer isn’t “arm for obliteration because the other side started it”

New comment by jjfoooo4 in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

jjfoooo4 — Sat, 25 Apr 2026 22:28:46 +0000

Even as someone highly interested in memory I don’t see it as a useful tool for coding. The source of truth for what a repo does or should do is the repo itself.

What you’re describing sounds more like code review guidelines, which can be explicitly brought into context at specific times during a change. A memory system is both too complex and less accurate for this

New comment by jjfoooo4 in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

jjfoooo4 — Sat, 25 Apr 2026 22:20:53 +0000

Simple vector similarity plus a cheap model to filter results works pretty well. Though ofc t does add tokens to your primary chat, which is the basic tradeoff of memory systems in general (in addition to latency)

New comment by jjfoooo4 in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

jjfoooo4 — Sat, 25 Apr 2026 22:18:11 +0000

I favor automatic recall, invisible to the agent. For memory creation, I find tool calls do a pretty good job, though I also like automatic memory creation on context compression.

I think with automatic creation you need async consolidation (calling it dreaming is a little dramatic for my taste).

My implementation is at Elroy.bot, I recently wrote about different approaches to agent memory here: https://tombedor.dev/approaches-to-agent-memory/

Coding agents have no moat

jjfoooo4 — Fri, 24 Apr 2026 20:36:13 +0000

Article URL: https://tombedor.dev/coding-agents-have-no-moat/

Comments URL: https://news.ycombinator.com/item?id=47895426

Points: 5

# Comments: 0

New comment by jjfoooo4 in "I cancelled Claude: Token issues, declining quality, and poor support"

jjfoooo4 — Fri, 24 Apr 2026 17:35:43 +0000

But these products are all drop in replacements for each other. I've recently favored Codex more than CC, just because rate limits got mildly annoying. I really didn't have to change anything about my workflow in doing that.

New comment by jjfoooo4 in "Deezer says 44% of songs uploaded to its platform daily are AI-generated"

jjfoooo4 — Mon, 20 Apr 2026 17:30:21 +0000

> My feeling is that if the AI is this good, the audience will just prompt the AI themselves and cut out the middleman.

I call this the instant imitator trap. If anything AI generates stands out from the slop, the slop generators will just imitate it, thus quickly making whatever standout quality from the "original" work also slop.

I wrote about it here: https://tombedor.dev/creativity/

New comment by jjfoooo4 in "Deezer says 44% of songs uploaded to its platform daily are AI-generated"

jjfoooo4 — Mon, 20 Apr 2026 17:27:15 +0000

From the press release, it's not all that clear what Deezer is doing about it. 44% of uploads getting less than 1% of non-fraudulent streams seems like a pretty strong reason to outright ban AI generated submissions.

For the non-fraudulent listens, I'm very curious how many of these are part of auto-generated playlists. Are people just being served this music as part of a feed, or are they actually seeking it out? I'd be very surprised if it was the latter.

The Instant Copy Trap Makes AI Creativity Impossible

jjfoooo4 — Fri, 17 Apr 2026 16:19:10 +0000

Article URL: https://tombedor.dev/creativity/

Comments URL: https://news.ycombinator.com/item?id=47807575

Points: 1

# Comments: 0

Can AI Be Creative?

jjfoooo4 — Wed, 15 Apr 2026 15:46:33 +0000

Article URL: https://tombedor.dev/creativity/

Comments URL: https://news.ycombinator.com/item?id=47780759

Points: 1

# Comments: 0

New comment by jjfoooo4 in "Nothing Ever Happens: Polymarket bot that always buys No on non-sports markets"

jjfoooo4 — Tue, 14 Apr 2026 16:11:42 +0000

It might be a bias in terms of the probability of events, but I'm not so sure this is a market inefficiency in terms of actual trading strategy. If true odds are 1% and the event is priced at 4%, I can sell NO for a 3% edge... but lose 100% once out of a hundred. Doesn't seem worth it!

Show HN: Excalicharts – Charting Library for Excalidraw

jjfoooo4 — Tue, 14 Apr 2026 00:20:08 +0000

I very frequently use Excalidraw for presentations and writing, but the charting ability is relatively limited. This project surfaces a CLI which supports a wider variety of chart types and parameters.

Outputting a .excalidraw file means that rather than endlessly tweaking parameters to get chart elements positioned just right, you can simply drag them around like any other Excalidraw scene.

Comments URL: https://news.ycombinator.com/item?id=47759670

Points: 4

# Comments: 0

New comment by jjfoooo4 in "Anthropic downgraded cache TTL on March 6th"

jjfoooo4 — Mon, 13 Apr 2026 15:09:35 +0000

Which I'm confused about - wouldn't decreasing the cache TTL increase compute demand?

New comment by jjfoooo4 in "Why AI Sucks at Front End"

jjfoooo4 — Mon, 13 Apr 2026 15:07:42 +0000

AI is a floor raiser, not a ceiling raiser

New comment by jjfoooo4 in "Bouncer: Block "crypto", "rage politics", and more from your X feed using AI"

jjfoooo4 — Mon, 13 Apr 2026 02:00:36 +0000

> you're going to end up systematically misinformed on political topics that people find outrageous.

That sounds... fine?

New comment by jjfoooo4 in "Ask HN: What Are You Working On? (April 2026)"

jjfoooo4 — Sun, 12 Apr 2026 23:22:28 +0000

I vibe coded a charting library for excalidraw that I’m working into my blog:

https://github.com/tombedor/excalicharts