Hacker News: alphabettsy

New comment by alphabettsy in "Claude Code weekly limits reduce by a third tomorrow"

alphabettsy — Tue, 18 Aug 2026 18:03:52 +0000

It might be objectively true for you.

Opus 5 is fine for me and works better and faster on low and medium than higher effort on prior versions. Same as 5.6 Sol compared to 5.5 or 5.4.

New comment by alphabettsy in "Credit card debt rises to $1.26T, nearing all-time record"

alphabettsy — Sun, 16 Aug 2026 00:57:04 +0000

A total measured over the entire US economy without adjusting for a variety of factors including inflation and population change seems like exactly the kind of thing you would expect from a news headline. How about average or per capita?

New comment by alphabettsy in "Claude Opus 5"

alphabettsy — Fri, 24 Jul 2026 20:28:43 +0000

As always, it requires evaluation with your work because I’m often finding grok to be much more expensive than the price would lead you to believe.

There’s also the frustration of it not quite being enough sometimes. It’s extremely capable, but I still find that it needs more concrete guidance and boundaries than other models.

New comment by alphabettsy in "The Safari MCP server for web developers"

alphabettsy — Fri, 03 Jul 2026 13:42:08 +0000

GitHub has been providing macOS runners for a while now.

Local Qwen isn't a worse Opus, it's a different tool

alphabettsy — Thu, 18 Jun 2026 03:04:20 +0000

Article URL: https://blog.alexellis.io/local-ai-is-not-opus/

Comments URL: https://news.ycombinator.com/item?id=48580209

Points: 493

# Comments: 253

New comment by alphabettsy in "SpaceX says it has agreement to acquire Cursor for $60B"

alphabettsy — Wed, 22 Apr 2026 04:16:03 +0000

That’s unfortunate. I’m not interested in using Musk associated products anymore than I have to.

New comment by alphabettsy in "Opus 4.7 to 4.6 Inflation is ~45%"

alphabettsy — Sat, 18 Apr 2026 18:07:12 +0000

I’m trying to understand how this is useful information on its own?

Maybe I missed it, but it doesn’t tell you if it’s more successful for less overall cost?

I can easily make Sonnet 4.6 cost way more than any Opus model because while it’s cheaper per prompt it might take 10x more rounds (or never) solve a problem.

New comment by alphabettsy in "Claude Opus 4.7 costs 20–30% more per session"

alphabettsy — Fri, 17 Apr 2026 20:58:01 +0000

The docs suggest not using max effort in most cases to avoid overthinking :shrug:

New comment by alphabettsy in "Trusted access for the next era of cyber defense"

alphabettsy — Tue, 14 Apr 2026 23:52:30 +0000

That’s been there for awhile.

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

alphabettsy — Mon, 13 Apr 2026 05:22:47 +0000

IMO it doesn’t handily beat it.

It’s typically equivalent, sometimes better, sometimes behind. Better at following a well defined plan, less good at concept exploration and planning imo.

At 1m context it’s basically the same price.

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

alphabettsy — Mon, 13 Apr 2026 05:19:06 +0000

Prompt cache expired?

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

alphabettsy — Mon, 13 Apr 2026 05:18:14 +0000

People keep saying this, but I’m not sure I buy it.

I was using both Codex and Claude Code heavily on some projects this weekend.

In one project Codex was screwing everything up and in another one absolutely killing it. I’ve seen the same from Claude.

In the bad Codex example it had the wrong idea and kept trying to figure out how to accomplish the same thing no matter how many times I attempt to correct it. Undoing the recent changes where it went down the wrong path was the only way to get things back on track.

I wonder if context poisoning is a bigger problem than people realize.

New comment by alphabettsy in "Pro Max 5x quota exhausted in 1.5 hours despite moderate usage"

alphabettsy — Mon, 13 Apr 2026 04:37:18 +0000

This is my experience too, and I always find these posts confusing. I consider myself a very heavy user 4-6 hrs a day and I never hit limits. I have on the $20 plan but not with Max.

New comment by alphabettsy in "Tesla Is Sitting on a Record 50k Unsold EVs"

alphabettsy — Sat, 04 Apr 2026 14:41:44 +0000

Remind me who was president in 2020..

New comment by alphabettsy in "FCC updates covered list to include foreign-made consumer routers"

alphabettsy — Tue, 24 Mar 2026 02:50:58 +0000

I believe they make satellite components not consumer hardware in the US

New comment by alphabettsy in "Claude struggles to cope with ChatGPT exodus"

alphabettsy — Mon, 09 Mar 2026 00:32:52 +0000

They claim it’s faster and it seems to be so for me.

New comment by alphabettsy in "How Bright Headlights Escaped Regulation – and Blinded Us All"

alphabettsy — Thu, 08 Jan 2026 13:49:03 +0000

It’s not an issue with limitations of current technology. In some cases it’s just greed and laziness. I’ve had two vehicles that have the ability to be more friendly to other drivers, but that functionality is only enabled outside of the U.S. (matrix headlights or the equivalent).

GM vehicles had been notorious for having poorly adjusted headlights from the factory. The fact that Xenon systems seemed to always come with auto leveling and LED often does not is crazy.

New comment by alphabettsy in "Build Your Own 100TB NAS in 2025: Complete TrueNAS Storage Guide"

alphabettsy — Thu, 25 Dec 2025 16:26:45 +0000

AI slop.

New comment by alphabettsy in "VS Code deactivates IntelliCode in favor of the paid Copilot"

alphabettsy — Tue, 16 Dec 2025 15:10:28 +0000

They’re fantastic imo. Don’t connect to them to the internet.

New comment by alphabettsy in "Kroger acknowledges that its bet on robotics went too far"

alphabettsy — Tue, 09 Dec 2025 02:48:06 +0000

Then put the warehouse on the first floor and put the store on top.

Lots of big cities have grocery stores with parking garages under them, doesn’t seem much different.