Hacker News: ed_mercer

New comment by ed_mercer in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

ed_mercer — Tue, 13 Oct 2026 00:35:49 +0000

When I saw 2 vCPU and 4GB, and then below that "4 GB persistent disk" I was like ooohhh it's the disk, not the memory. But it IS actually 4GB memory + 4GB disk.

New comment by ed_mercer in "Show HN: Destroy Any Website with Stickman"

ed_mercer — Tue, 29 Sep 2026 02:44:27 +0000

This was so fulfilling to do on x.com

New comment by ed_mercer in "Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms"

ed_mercer — Tue, 29 Sep 2026 01:08:47 +0000

jev is optimized for it, a standard LLM isn't and it also costlier and slower.

New comment by ed_mercer in "Ember-1"

ed_mercer — Mon, 28 Sep 2026 02:16:31 +0000

So are they going to release this tuned model? Or keep it for themselves?

New comment by ed_mercer in "Plan mode is dead"

ed_mercer — Sat, 26 Sep 2026 02:27:28 +0000

I also noticed this personally. Consider when an agent says

"Should I start with the spec, or go straight to building it?

Unless you're working on a super crucial piece of engineering, you can probably get away with going straight to building it. Even if something doesn't go the way you intended, I find that it's usually faster to correct the agent later, once the initial implementation is in place. It's more of an iterative approach to building and I feel that it is less cognitively demanding.

New comment by ed_mercer in "Apple has added persistent 'ads' to iOS, and it's driving users crazy"

ed_mercer — Tue, 22 Sep 2026 23:35:12 +0000

Except for VRR, HDR, touch id, video encoding and a sleep mode that doesn't drain your battery.

New comment by ed_mercer in "HarnessTax: How Much Does the Harness Matter for Coding Agents?"

ed_mercer — Thu, 17 Sep 2026 00:32:37 +0000

Does this extend to open models like GLM 5.3? This would mean that simply changing the harness to Pi reduces cost in half?

New comment by ed_mercer in "Apple Reference Image: A New Approach for Verified Photography"

ed_mercer — Wed, 16 Sep 2026 05:09:58 +0000

Lots of criticism here but I think this is extremely promising. When this tech is extended to videos and perhaps even other forms of media, I think it has the potential of stopping all slop!

New comment by ed_mercer in "Chess.com Leak Exposes 7.3M Users, Evidence Points to Scraping"

ed_mercer — Mon, 14 Sep 2026 05:13:17 +0000

email? Is a user's email up for grabs just like that?

New comment by ed_mercer in "google.com/goto: Google's anti-scraping update"

ed_mercer — Sat, 12 Sep 2026 05:28:21 +0000

>I do enjoy using their free AI

It's really not free. You're paying with your data.

New comment by ed_mercer in "OpenAI Agents API"

ed_mercer — Fri, 11 Sep 2026 04:18:29 +0000

you mean something like step level debugging for agents?

New comment by ed_mercer in "Apple Watch Ultra 4"

ed_mercer — Thu, 10 Sep 2026 01:35:52 +0000

Meanwhile, 7 years on my F-91W

New comment by ed_mercer in "216M Spy TVs – The LG Smart TV Problem [video]"

ed_mercer — Tue, 08 Sep 2026 01:38:41 +0000

Why would you ever connect a TV to the internet in the first place?

New comment by ed_mercer in "Finder is so frustrating and has been since day one"

ed_mercer — Mon, 07 Sep 2026 04:13:40 +0000

Awesome write-up, thank you! This makes me want to try this out as well.

New comment by ed_mercer in "Finder is so frustrating and has been since day one"

ed_mercer — Mon, 07 Sep 2026 02:22:26 +0000

Hi, can you elaborate on this? Why not use Asahi Linux?

New comment by ed_mercer in "Maybe We Shouldn't Be Reviewing All This Code"

ed_mercer — Wed, 02 Sep 2026 23:51:17 +0000

Fable-class models IMO are now capable enough to maintain your code as well.

New comment by ed_mercer in "Warp builds self-improving agents on Claude"

ed_mercer — Sun, 30 Aug 2026 00:15:25 +0000

This is all great until you change or upgrade to a newer model, and you can start over again because some of the directions/rules are now part of the model.

New comment by ed_mercer in "My Business Is Dying"

ed_mercer — Fri, 28 Aug 2026 08:19:21 +0000

OP was doing 30K USD MRR, not sure why he needs to find a job at all. Did he spend it all?

New comment by ed_mercer in "Alphabet stock sheds $700B as AI bills climb"

ed_mercer — Fri, 28 Aug 2026 08:11:18 +0000

> which has even seen Google co-founder Sergey Brin return to day-to-day operations

This is false, Brin already returned to active work at Google in early 2023. https://www.forbes.com/sites/richardnieva/2023/01/31/sergey-...

New comment by ed_mercer in "Claudette: Make Claude stop talking like a BuzzFeed article"

ed_mercer — Sat, 22 Aug 2026 04:20:25 +0000

I personally got used to the claudisms and think people are making too big of a deal out of it. Yes it says load-bearing and caveat a lot, but at least you know behind the scenes what meaning it's assigning to certain situations.