Hacker News: StanAngeloff

New comment by StanAngeloff in "The CSS Zen Garden dream, finally shipped"

StanAngeloff — Tue, 15 Sep 2026 18:24:51 +0000

The below is a selected copy of the blog post, unbelievable that it didn't get unslopped:

> [..] , and on a site like this one that matters more than architectural purity. [..] Nothing in it depends on a build step [..] That distinction is worth keeping in mind [..] What matters is [..]

New comment by StanAngeloff in "Fable 5 on par with GPT-5.5 in Artificial Analysis Coding Agent Index"

StanAngeloff — Fri, 12 Jun 2026 10:22:21 +0000

> https://artificialanalysis.ai/agents/coding-agents?coding-ag...

This is the full URL that does a composite average across DeepSWE, Terminal-Bench and SWE-Atlas-QnA. Models are measured in their respective harnesses.

What is surprising to me is that Claude Code + Fable 5 (max) is on par with Codex + GPT-5.5 (xhigh)... yet Fable burnt through 1M extra tokens.

Fable 5 on par with GPT-5.5 in Artificial Analysis Coding Agent Index

StanAngeloff — Fri, 12 Jun 2026 10:20:53 +0000

Article URL: https://artificialanalysis.ai/agents/coding-agents

Comments URL: https://news.ycombinator.com/item?id=48502186

Points: 4

# Comments: 1

New comment by StanAngeloff in "Ask HN: What was your "oh shit" moment with GenAI?"

StanAngeloff — Sat, 06 Jun 2026 06:27:01 +0000

One of the many SaaS products we use at Day Job chose to gatekeep its MCP behind an enterprise plan. A brief Claude Code session later and a better, more feature-full MCP than the official was reverse-engineered from internal APIs by Opus.

Teaching tmux to babysit my Claude Code agents

StanAngeloff — Fri, 29 May 2026 18:09:53 +0000

Article URL: https://blog.angeloff.name/post/2026/05/29/teaching-tmux-to-babysit-my-claude-code-agents/

Comments URL: https://news.ycombinator.com/item?id=48327021

Points: 3

# Comments: 0

New comment by StanAngeloff in "Claude Opus 4.8"

StanAngeloff — Fri, 29 May 2026 12:00:42 +0000

> [..] Early access users and teams inside Anthropic have been using dynamic workflows for a wide range of use cases [..]

> ### Rewriting Bun with dynamic workflows

> An example of what dynamic workflows can unlock at scale is the recent rewrite of Bun. Jarred Sumner used dynamic workflows to port Bun from Zig to Rust [..]

That's very interesting to hear!

New comment by StanAngeloff in "Claude.ai unavailable and elevated errors on the API"

StanAngeloff — Tue, 28 Apr 2026 18:42:01 +0000

All it took for Codex to resume a stalled Claude Code session:

> I'm working with Claude Code on session aaaaaaaa-bbbb-1223-3445-abcdefabcdef which I'd like to hand-off to you, do you know how to read the session, my input and Claude's output so we can resume where I left off?

gpt-5.5, medium effort. "Resumed" session fully in under 2 minutes. Outages like today's are so common that I've now got the time to re-evaluate Codex every other day.

New comment by StanAngeloff in "Show HN: Ctx – a /resume that works across Claude Code and Codex"

StanAngeloff — Tue, 21 Apr 2026 19:21:03 +0000

I've actually had the same itch and decided to give it a go ... So far I'm one year into the project, learned a ton and highly recommend to anyone who'd listen - try writing you own harness. It can be fun, it can be intoxicating, it can also be boring and mundane. However you'll learn so much along the way, even if you thought you already were well versed.

New comment by StanAngeloff in "CC – API Error: 500"

StanAngeloff — Mon, 13 Apr 2026 15:49:06 +0000

Dupe https://news.ycombinator.com/item?id=47753643

New comment by StanAngeloff in "Claude.ai down"

StanAngeloff — Mon, 13 Apr 2026 15:47:09 +0000

This is affecting lots of users (myself included) and has prompted an official status page update, so it's very much real for users, but I guess only on claude.ai. Are you using Claude models through something/someone else?

New comment by StanAngeloff in "[dead]"

StanAngeloff — Mon, 13 Apr 2026 15:45:19 +0000

Dupe https://news.ycombinator.com/item?id=47753643

New comment by StanAngeloff in "Ask HN: Is Claude Down Again?"

StanAngeloff — Mon, 13 Apr 2026 15:43:23 +0000

Yes https://news.ycombinator.com/item?id=47753643

New comment by StanAngeloff in "Tell HN: Claude Opus elevated "Internal server error" again"

StanAngeloff — Mon, 13 Apr 2026 15:42:40 +0000

Officially down https://status.claude.com/incidents/6jd2m42f8mld

Discussion: https://news.ycombinator.com/item?id=47753643

Tell HN: Claude Opus elevated "Internal server error" again

StanAngeloff — Mon, 13 Apr 2026 15:40:35 +0000

No official report as of yet on https://status.claude.com/ however my team's sessions across different accounts have been ridden with errors the last 5-10 minutes.

This is more of a "it's not just you" post for those affected since Claude's status page is useless ("All Systems Operational"!)

Comments URL: https://news.ycombinator.com/item?id=47753630

Points: 3

# Comments: 1

New comment by StanAngeloff in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

StanAngeloff — Mon, 06 Apr 2026 17:03:41 +0000

I did my usual thing today where I asked a Sonnet 4.6 agent to code review a proposed design plan that was drafted by Opus 4.6 - I do this lately before I delved into the implementation. What it came back with was a verbose output suggesting that a particular function `newMoneyField` be renamed throughout the doc to a name it fabricated `newNumeyField`. And the thing was that the design document referenced the correct function name more than a few dozen times.

This was a first for me with Sonnet. It completely veered off the prompt it was given (review a design document) and instead come out with a verbose suggestion to do a mechanical search and replace to use this newly fabricated function name - that it event spelled incorrectly. I had to Google numey to make sure Sonnet wasn't outsmarting me.

New comment by StanAngeloff in "Claude Code is unusable for complex engineering tasks with the Feb updates"

StanAngeloff — Mon, 06 Apr 2026 16:52:08 +0000

I missed that from the long issue, thanks for pointing it out! My experience with Opus today was riddled with these to the point where it was driving me completely mental. I've rarely seen those self-contradictions before, and nothing on my setup has changed - other than me forcing Opus at --effort max at startup.

I wonder if this is even more exaggerated now through Easter, as everyone’s got a bit extra time to sit down and with Claude. That might be pushing capacity over the limit - I just don’t know enough about how Antropic provision and manage capacity to know if that could be a factor. However quality has gotten really bad over the holiday.

New comment by StanAngeloff in "Claude Code is unusable for complex engineering tasks with the Feb updates"

StanAngeloff — Mon, 06 Apr 2026 16:45:10 +0000

I used to one-shot design plans early in the year, but lately it is taking several iterations just to get the design plan right. Claude would frequently forget to update back references, it would not keep the plan up to date with the evolving conversation. I have had to run several review loops on the design spec before I can move on to implementation because it has gotten so bad. At one point, I thought it was the actual superpowers plugin that got auto-updated and self-nerfed, but there weren't any updates on my end anyway. Shrug.

New comment by StanAngeloff in "Claude Code is unusable for complex engineering tasks with the Feb updates"

StanAngeloff — Mon, 06 Apr 2026 14:31:31 +0000

You say you've used it for months, I wonder if the example you gave was recent and if you've been noticing an overall degradation in quality or it's been constantly bad for you?

New comment by StanAngeloff in "Claude Code is unusable for complex engineering tasks with the Feb updates"

StanAngeloff — Mon, 06 Apr 2026 14:14:36 +0000

That is the kind of thing that I've been fighting by being super explicit in CLAUDE.md. For whatever reason, instead of being much more thorough and making sure that files are being changed only after fully understanding the scope of the change (behaviour prior to Feb/Mar), Claude would just jump to the easiest fix now, with no backwards compatibility thinking and to hell with all existing tests. What is even worse is I've seen it try and edit files before even reading them on a couple of occasions, which is a big red flag. (/effort max)

Another thing that worked like magic prior to Feb/Mar was how likely Claude was to load a skill whenever it deduced that a skill might be useful. I personally use [superpowers][1] a lot, and I've noticed that I have to be very explicit when I want a specific skill to be used - to the point that I have to reference the skill by name.

[1]: https://github.com/obra/superpowers

New comment by StanAngeloff in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

StanAngeloff — Mon, 06 Apr 2026 13:54:05 +0000

(Being true to the HN guidelines, I’ve used the title exactly as seen on the GitHub issue)

I was wondering if anyone else is also experiencing this? I have personally found that I have to add more and more CLAUDE.md guide rails, and my CLAUDE.md files have been exploding since around mid-March, to the point where I actually started looking for information online and for other people collaborating my personal observations.

This GH issue report sounds very plausible, but as with anything AI-generated (the issue itself appears to be largely AI assisted) it’s kind of hard to know for sure if it is accurate or completely made up. _Correlation does not imply causation_ and all that. Speaking personally, findings match my own circumstances where I’ve seen noticeable degradation in Opus outputs and thinking.

EDIT: The Claude Code Opus 4.6 Performance Tracker[1] is reporting Nominal.

[1]: https://marginlab.ai/trackers/claude-code/