Silent model quality regressions ("it got dumber")

i dont think they've nerfed it did you use api or via subscription(which might make sense) api has been pretty stable for me. personally i like 4 Argon, it's very clever for me in a very different way comparing to the other two (especially via api) but when it comes to the google products.. sigh. nobody who's actually working on these products really cares about them in google now (maybe notebooklm is the rare excep…

LewisOrton · Oct 28, 2026 · comment in “Gemini 4 Carbon”

Google doesn't have enough compute to serve there own customers. I have AI pro via a promo offer with my phone and Antigravity has been almost unusable the past week, exceptionaly slow and they completely nerfed the promo accounts by not giving access to Argon or the new claude models as well as making Flash 3.8 much worse.

ChildOfChaos · Oct 22, 2026 · comment in “OpenAI models are coming to Google Cloud”

1. AI is nerf'ed, helpful, restrictive, annoying, repetitive.

pizzafeelsright · Oct 5, 2026 · comment in “Infidel goes wild”

Keeping a heavy IDE open, waiting for it to load, and then opening yet another terminal tab just to run an agent was more overhead than it was worth. It got worse with multiple agents — one terminal per agent, and my desktop turned into a mess of windows.

asdsa112 · Aug 3, 2026 · story in “Show HN: AgentCodeGUI – Multi-Account Desktop GUI for Claude Code and Codex”

The old app version was actual "chat" application focused on conversations UI, new one seemingly got merged with Codex and conversations are an afterthought - you have to navigate to them, the history is unusable, everything got worse.

midnight_eclair · Jul 14, 2026 · comment in “ChatGPT Mac App ruins Chats interface by merging with Codex”

Then it got lobotomized and it's never been the same after that nerf. 4.7 came along and it too was disappointing—not unlike 4.8, which despite feeling a smidge smarter, tends to write word salad and is basically unusable for some workflows.

airstrike · Jun 23, 2026 · comment in “Will It Mythos?”

GPT is unusable, untrustworthy, unreliable now [may 2026] - SouthPark poked fun at GPT calling everything a brilliant idea and the retaliation by "Open"AI was to nerf any response that didn't denigrate the user and inflate the LLM.

summarybot · May 15, 2026 · comment in “Codex is now in the ChatGPT mobile app”

The remote agent has access to all the docs and instructions in my repo and most of the time gives me a decent draft I just need to polish later. I unsubscribed from Claude after the performance regressions around the time of the Opus 4.7 update made it unusable.

teodosin · May 15, 2026 · comment in “Codex is now in the ChatGPT mobile app”

Not doing that, presenting as more capable/knowing than one probably is, is what destroys trust immediately the moment it's sniffed out that AI was used to write something. It's irresponsible, a self-nerf, and it's annoying.

trueno · Apr 19, 2026 · comment in “Zero-Copy GPU Inference from WebAssembly on Apple Silicon”

Did they nerf the model or was it changes to Claude code? I agree it got frustrating.

ec109685 · Apr 18, 2026 · comment in “Measuring Claude 4.7's tokenizer costs”

Kdenlive has some unfortunate performance regression when working with larger projects with many clips. I managed to track down a few of them while evaluating Claude Code a while back (mostly certain actions doing O(n) scans over all clips every mouse event needing debouncing), and got it mostly back down to tolerable levels again, but have been holding onto them because unsolicited drive by AI PRs are very annoying…

marginalia_nu · Apr 18, 2026 · comment in “State of Kdenlive”

Did people enjoy Claude routinely disregarding their instructions? Not really sure I understand, I truly found 4.6 immensely frustrating (from the getgo, not just the "pre-nerf" version, whatever that means).

Jweb_Guru · Apr 18, 2026 · comment in “Measuring Claude 4.7's tokenizer costs”

Been having this feeling that things have got worse recently but didn't think it could be model related. The most frustrating aspect recently (I have learned and accepted that Claude produces bad code and probably always did, mea culpa) is the non-compliance.

skippyboxedhero · Apr 6, 2026 · comment in “Issue: Claude Code is unusable for complex engineering tasks with Feb updates”

How it works: You wrap your client with our SDK in only a couple of lines. From there, we detect drift for you: - Wrong tool invocations - Misunderstood intents - Hallucinations - Quality regressions over time.

anayrshukla · Mar 11, 2026 · story in “Launch HN: Sentrial (YC W26) – Catch AI agent failures before your users do”

Yeah - Google really tried to get people to use Google+ but it always sucked. YouTube, while Google nerfed and downgraded it, still works to some extent, though AI generated "content" is such a waste of time.

shevy-java · Feb 4, 2026 · comment in “Microsoft's Copilot chatbot is running into problems”

I suspect that’s why Alexa and Google Assistant got worse when they became LLM based and my narrow use cases don’t suffer those problems when I started implementing LLM based solutions. And I am purposefully yada yada yadaing some of the technical complexities and I hate the entire “appeal to authority” thing.

raw_anon_1111 · Jan 13, 2026 · comment in “Apple picks Gemini to power Siri”