42 engineers on Hacker News describe using Claude Opus first-hand: 17 endorse it, 4 regret it, 6 are mixed.
“Opus 5.5 is much better than Grok”
endorse · personal · senordevnyc · 2026-11-05 · source ↗ · wrong label?“It codes well when you tell it what to do, but it is still dumb about what is the real problem”
mixed · personal · flaburgan · 2026-11-05 · source ↗ · wrong label?“So yes, even recent models do utterly stupid shit pretty frequently”
regret · personal · floren · 2026-11-02 · source ↗ · wrong label?“State of the art agents don't usually need such fixed guidance anymore. I've been using Opus 5.5 with Xcode”
endorse · production · jshier · 2026-11-02 · source ↗ · wrong label?“I've been using opus 5.5 for decompiling a late 90s PC game based on an incomplete leak of the source code and haven't hit any kind of restrictions or push back.”
endorse · personal · xyzsparetimexyz · 2026-11-01 · source ↗ · wrong label?“Even with Opus or Astra I will spot cleanup issues frequently.”
mixed · production · Aurornis · 2026-10-30 · source ↗ · wrong label?“I use Opus 5.5 at work and it's still much better than this”
endorse · production · almindor · 2026-10-29 · source ↗ · wrong label?“I just got opus to valid this now and it found another issue with our scale codebook gen, which I will fix now.”
endorse · production · slimbuck · 2026-10-29 · source ↗ · wrong label?“Opus 5.5 in comparison is a bit more verbose... but is still vastly capable and I can read its output”
endorse · personal · n0on3 · 2026-10-28 · source ↗ · wrong label?“I had been using Opus 4.6 with no problems until yesterday, then it seemed like it was missing things constantly, introducing random bugs”
regret · personal · nico · 2026-10-25 · source ↗ · wrong label?“Opus 5.5 can fix everything but the guardrails trigger too easily.”
mixed · personal · arjie · 2026-10-23 · source ↗ · wrong label?“I've been using Opus 5.5 for pretty much everything”
endorse · personal · malisper · 2026-10-23 · source ↗ · wrong label?“At work I've been using about $500 worth of copilot credits (mostly on Anthropic's opus model) to do work that would previously require a team”
endorse · production · Roark66 · 2026-10-23 · source ↗ · wrong label?“Opus 5.5 is still the smartest, but DS 4.1's speed and price more than make up for the "intelligence" gap.”
endorse · personal · ilitirit · 2026-10-17 · source ↗ · wrong label?“Apparently, it worked better with lightning and texture improvements than both Fabel and Astra”
endorse · personal · Livia_Zaharia · 2026-10-05 · source ↗ · wrong label?“since Opus 4.6 when models got really good... But the model quality has varied.”
mixed · production · hbn · 2026-09-29 · source ↗ · wrong label?“I still have to baby sit Astra and opus 5.5 into reusing existing structures/functions, not reinventing the wheels”
mixed · production · toasty228 · 2026-09-27 · source ↗ · wrong label?“It has the same annoying cadence and writing style with slightly less prominent claudisms.”
regret · personal · dgroshev · 2026-09-22 · source ↗ · wrong label?“Obviously Opus is still substantially better model.”
endorse · production · _pdp_ · 2026-07-06 · source ↗ · wrong label?“Opus 4.8 is frankly writing better software than what I've seen over the previous decades in non-tech enterprise.”
endorse · production · Quothling · 2026-06-10 · source ↗ · wrong label?“My coworkers have independently used Opus for optimization suggestions on services in prod and they've led to much better performance (3x in some cases).”
endorse · production · minimaxir · 2026-04-23 · source ↗ · wrong label?“Three months ago, with opus4.5, I would have said that the productivity improvement was ~10% for my whole team.”
endorse · production · orwin · 2026-03-08 · source ↗ · wrong label?“Where it fails hard is in the more subtle areas of the code, like good design, best practices, good taste, dry, etc.”
mixed · production · _pdp_ · 2026-01-07 · source ↗ · wrong label?“The technical moat is still the superiority of the model, and others are bound to catch up there.”
endorse · personal · atombender · 2025-12-31 · source ↗ · wrong label?“it has been working the best of any of the system I have tried. Very happy with it so far.”
endorse · personal · djinnrutger · 2025-12-17 · source ↗ · wrong label?“Due to unexpected capacity constraints, Claude is unable to respond to your message.”
regret · personal · crystal_revenge · 2025-12-14 · source ↗ · wrong label?“We are still internally testing Opus 4.5, which is the first version of Opus priced low enough to use in production. It's very clever”
endorse · production · samuelknight · 2025-12-02 · source ↗ · wrong label?“I was only using Opus 5.5 before as I wanted the highest quality”
neutral · personal · brabel · 2026-11-05 · source ↗ · wrong label?“I started with opus 4.8 limited to 200k context as the supervisor”
neutral · personal · Roark66 · 2026-11-02 · source ↗ · wrong label?“this is coming from someone who just sticks with Opus 5.5 mostly across the board”
neutral · production · nater5000 · 2026-10-28 · source ↗ · wrong label?“I asked Opus 5.5 to vibe code a passkey auth solution in Go a few times without saying anything specific about userVerification.”
neutral · personal · oefrha · 2026-10-11 · source ↗ · wrong label?“So we switched our agent entirely from Opus to Kimi and DeepSeek, and improved Twin through experiments on production traffic.”
neutral · production · merciertwin · 2026-09-29 · source ↗ · wrong label?“Fable for me was a step above opus.”
neutral · personal · anukin · 2026-09-02 · source ↗ · wrong label?“I must admit, Opus 4.8 is quite expensive, and the costs accumulate quickly.”
neutral · production · ianberdin · 2026-07-13 · source ↗ · wrong label?“My own experience w/ 4.6 and 4.7 are that I don't firmly grasp any capabilities improvements over my memory of 4.5”
neutral · production · NiloCK · 2026-05-28 · source ↗ · wrong label?“my coding agent (Opus 4.7 based) says things like "this is the kind of thing that will blow up at 2am six months from now" all the time.”
neutral · personal · projectazorian · 2026-05-15 · source ↗ · wrong label?“With Opus4.5, Gemini 3 and gpt 5.2, it's now 20%, maybe 50% if we only talk about personal code output.”
neutral · production · orwin · 2025-12-28 · source ↗ · wrong label?“I've been using composer-1 in Cursor for a few weeks and also switching back and forth between it, Gemini Flash 3, Claude Opus 4.5, Claude Sonnet 4.5 and GPT 5.2.”
neutral · production · santoriv · 2025-12-19 · source ↗ · wrong label?“those are the daily drivers we use internally w/ Letta Code”
neutral · production · pacjam · 2025-12-17 · source ↗ · wrong label?“I've been using Claude Code + Opus for side projects.”
neutral · personal · giancarlostoro · 2025-12-14 · source ↗ · wrong label?“I passed Bytedance's official prompting guide, OPs prompt, and your feedback to Claude Opus 4.5 and got this prompt to create a new image”
neutral · personal · BoorishBears · 2025-11-26 · source ↗ · wrong label?“Using opus our best guess is that it's unloading chunks and the GC is happening.”
neutral · personal · jonathanlydall · 2021-09-04 · source ↗ · wrong label?