Sabitlenmiş Tweet
Kaan
561 posts
Kaan retweetledi
CLAUDE OPUS 4.6 IS NERFED.
BridgeBench just proved it.
Last week Claude Opus 4.6 ranked #2 on the Hallucination benchmark with an accuracy of 83.3%.
Today Claude Opus 4.6 was retested and it fell to #10 on the leaderboard with an accuracy of only 68.3%.
A 98% increase in hallucination.
bridgebench.ai just confirmed that Claude Opus 4.6 has reduced reasoning levels and is nerfed.
English
Okay, Claude started making a lot of mistakes, but "it can’t be that stupid," I thought, and I tried it myself.
SilenceÇaPrompt@SilenceCaPrompt
🚨 FLASH : Opus 4.6 a été silencieusement dégradé et les utilisateurs le prouvent avec des tests. 5 fenêtres de suite en échec sur Opus 4.6. Opus 4.5 passe à chaque fois. Les gens annulent leurs plans Max pour un nerf qu'Anthropic n'a jamais annoncé.
English
Kaan retweetledi
Anthropic is secretly nerfing Opus 4.6 and hoping you won't notice.
I have proof:
Evidence is stacking up that 4.6 is getting brutally quantized to handle demand, while 4.5 stays pristine.
Fresh benchmarks reveal a devastating gap:
> Opus 4.6: Logic failures on repeat.
> Opus 4.5: Nails it every single time.
One dev now runs a "Quantization Canary"
a diagnostic prompt fired at the start of every session.
He just watched five 4.6 windows fail back-to-back.
His verdict: "Switched to 4.5 and it felt like I finally got my brain back."
If the model feels dumber lately, trust your gut.
You're being throttled so they can save on compute.
Switch to 4.5. The difference is night and day.
Om Patel@om_patel5
OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself
English
Kaan retweetledi
Opus is so unbelievably nerfed today, it's like talking to a model from 2-3 years ago. What is going on
English
Kaan retweetledi
Kaan retweetledi
Now that every company shares the same aesthetic… what should we do next? we turned the internet black and white, dithering, particles, ASCII everywhere. Maybe it’s time to step into the light.
English
Kaan retweetledi
That mf winning fr bcs of Antrophic’s bad policy. lol
Sam Altman@sama
To celebrate 3 million weekly codex users, we are resetting usage limits. We will do this every million users up to 10 million. Happy building!
English
Kaan retweetledi
Talking as a Max subscriber, Claude got dumber fr, and the context limit is filling up faster than ever. Although I’ve always seen that @bcherny has guided folks in the right direction, this time Boris went wrong too.
Om Patel@om_patel5
SOMEONE ACTUALLY MEASURED HOW MUCH DUMBER CLAUDE GOT. THE ANSWER IS 67%. the data shows Opus 4.6 is thinking 67% less than it used to. anthropic said nothing until the numbers went public. then suddenly Boris Cherny (creator of Claude Code) shows up on the GitHub issue. users are calling it "AI shrinkflation" (same price, less intelligence) we already know from the leaked source code that they have an internal switch that keeps the models working to their full extent for anthropic employees. in the last week Claude went from WOW to being a more restricted and expensive version of ChatGPT. people are saying Anthropic is deliberately downgrading Opus to save compute for training Mythos, their next model.
English
Kaan retweetledi
Me trying to learn Claude Code to avoid losing my job, when there are much bigger issues in 2026
English
Kaan retweetledi
Turkiye mentioned 🇹🇷🇹🇷🇹🇷🇹🇷🇹🇷🇹🇷
Barchart@Barchart
BREAKING 🚨: Turkey Turkish Lira falls to an all-time low against the U.S. Dollar 🇹🇷📉
English
@MarceloRet41877 @bcherny ngl, I had to agree as a customer who wants more, but I didn't hit the limits during the past 3 months even tho i use it every day properly.
English
@bcherny But how exactly are we supposed to use all of this on the $200/mo plan when we’re already hitting usage limits after the first two prompts at 8 AM?
English
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.
Here goes.
English
Google Maps for Venture Capital. Founders and VCs, this is for you:
We built OpenMap. A visual directory of 16,000+ VCs, angels, and family offices worldwide.
Think of it as Google Maps for Venture Capital.
👉 Comment "map" for free access
Here's what's inside:
→ Visual map of investors actively looking for deals
→ Search "investors in Paris," "deeptech VCs," "family offices"
→ Find intros through LinkedIn + Gmail connections
→ Submit your deck directly to investors
If you're a VC, you should be on this map.
If you're a founder, you need to know this map.
👉 Comment "map" I'll DM you the link.
Make sure to follow me to receive my DM.
English