Hacker News: ai_slop_hater

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

ai_slop_hater — Mon, 06 Apr 2026 21:33:57 +0000

Alright, I just tested that setting and it doesn't work.

https://i.imgur.com/MYsDSOV.png

I tested because I was porting memories from Claude Code to Codex, so I might as well test. I obviously still have subscription days remaining.

There is another comment in this thread linking a GitHub issue that discusses this. The GitHub issue this whole HN submission is about even says that Anthropic hides thinking blocks.

New comment by ai_slop_hater in "Intelligent people are better judges of the intelligence of others"

ai_slop_hater — Mon, 06 Apr 2026 21:05:22 +0000

Does that mean we should use a larger model as judge for evals, not a smaller one?

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

ai_slop_hater — Mon, 06 Apr 2026 20:43:38 +0000

I read his comment and still replied. I think his claim that nobody reads thinking blocks and that thinking blocks increase latency is nonsense. I am not going to figure out which settings I need to enable because after reading this thread I cancelled my subscription and switched over to Codex. Because I had the exact same experience as many in this thread.

Also what is that "PR advice"—he might as well wear a suit. This is absolutely a nerd fight.

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

ai_slop_hater — Mon, 06 Apr 2026 18:53:55 +0000

Thanks. I was referring to the fact that Anthropic, in their API, prohibits setting temperature when thinking is enabled.

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

ai_slop_hater — Mon, 06 Apr 2026 18:46:41 +0000

Huh, I wonder if that's why you cannot change the temperature when thinking is enabled. Do you have a link for the paper?

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

ai_slop_hater — Mon, 06 Apr 2026 18:31:29 +0000

> You can add a bias to make it more or less likely for a model to generate a particular token, and that's how budgets work

Do you have a source for this? I am interested in learning more about how this works.

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

ai_slop_hater — Mon, 06 Apr 2026 18:23:32 +0000

I also have similar experience with their API, i.e. some requests get stalled for minutes with zero events coming in from Anthropic. Presumably the model does this "extended thinking" but no way to see that. I treat these requests as stuck and retry. Same experience in Claude Code Opus 4.6 when effort is set to "high"—the model gets stuck for ten minutes (at which point I cancel) and token count indicator doesn't increase.

I am not buying what this guy says. He is either lying or not telling us everything.

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

ai_slop_hater — Mon, 06 Apr 2026 18:05:32 +0000

> This beta header hides thinking from the UI, since most people don't look at it.

I look at it, and I am very upset that I no longer see it.

New comment by ai_slop_hater in "Ask HN: Is there any interest in a native Qt/C++ Discord client?"

ai_slop_hater — Sun, 05 Apr 2026 10:32:50 +0000

I can already tell it's vibe coded because you listed all those "production" features like exponential back-off and rate limiting.

New comment by ai_slop_hater in "Extra usage credit for Claude to celebrate usage bundles launch (Pro, Max, Team)"

ai_slop_hater — Sat, 04 Apr 2026 00:51:21 +0000

Why would I want this, if I already have a subscription?

New comment by ai_slop_hater in "Show HN: Mtproto.zig – High-performance Telegram proxy with DPI evasion"

ai_slop_hater — Sat, 04 Apr 2026 00:27:33 +0000

Have you built it, or have you had AI build it?