Vibe coders have long suspected that the models and reasoning effort they pay for have been quietly downgraded since release. For instance, on October 23, a user filed an issue on GitHub saying they had requested Sol 6.1 at xhigh in Codex but the account UI showed Luna. Either the model selection or the UI is wrong. Opus 5.5, which scores higher than Fable 5.1 in Anthropic’s benchmarks yet costs less, is on everyone’s radar as a potential next victim. In this context, when Opus is accused of being “nerfed”, users are asking for consistency, not a one-time peak score.
Tagged Anthropic
How to Remedy Unwanted Annual Claude Pro Subscription
My annual Claude Pro plan renewed in late July. Opus 5 underperformed with a greater token cost, and by late August I asked Fin, Anthropic’s support chatbot, for a refund over the performance problems. It replied that my purchase “doesn’t meet our refund eligibility criteria due to falling outside of the timeframe for our policy”. Time for a creative solution.
Big Surprise Week from Claude and Codex: Opus 5.5, GPT-6 Sol, and Luna
Anthropic released Claude Opus 5.5 on September 22, the same day OpenAI released GPT-6 Sol and Luna. OpenAI is making its lower-end models cheaper, while Anthropic is still pushing upward. On price to performance, Opus 5.5 now beats Fable 5.1, which makes one wonder who would still use Fable.
Fable 5 Now Included in Max Subscription
Fable 5 saga is finally coming to an end with Anthropic deciding to include the flagship model in Max. Since I am on Max tier for this month temporarily, the announcement is disappointing in two ways: a. Fable won’t be available on a similar price tier as GPT 5.6 Sol, and b. Fable is simply too inefficient when it comes to token counts compared to Sol. Whichever way you cut it, you can get a better deal from Codex.
Fable 5 Trial Extended, Again
The great game of chicken is afoot. Fable 5 trial period is extended, yet again, to July 19th. Albeit anecdotal, there are numerous developers sharing similar stories about the cost performance of the new ChatGPT model, GPT-5.6 Sol. The community consensus agrees Fable 5 and Sol are both frontier models delivering similar results. What’s staggering in these accounts of ChatGPT comparison is not its mere performance. The current consensus seems to be running around a third or a quarter of the cost of running Fable 5.
Fable 5 Trial Extended
Fable 5’s trial period got an extension. If you had a chance to try it on an existing subscription, you already know whether it worked out for your actual project. There’s no stronger evidence than that. For me, Fable 5’s capability was amazing in its own right — but not at usage-based pricing.
Fable 5 Is Back, Also Sonnet 5 Is Out
Anthropic announced Sonnet 5 this week, described to be as capable as Opus 4.8 but cheaper. Rough timing — Fable 5’s return ate all the attention. I haven’t had the chance to do any coding with it in-depth yet. But from the limited exchange I had over chat, Sonnet 5 still struggled with technical specs. For any technical discussion, I had better luck with Gemini Flash 3.5. In terms of output, Sonnet became incredibly verbose. There is no trace of the laconicism I had noticed in Sonnet 4.
What Remains of Fable 5 Ban
Apple said Apple Intelligence would bring AI to its brand. It was a broken promise, unless Genmoji is to be considered a success. Apple is now saying the new Siri AI will deliver the promises they made back in 2024. Neither iOS 27 nor macOS Golden Gate has been officially released (available only in beta), but this definitely marks the beginning of the full transition toward AI-centrism in consumer OS. The dependency is real now — local or cloud, there’s no opting out.
How to Skip All Claude Code Permission Prompts on VS Code
Continuing on from yesterday’s Claude Code piece, Anthropic provides an official extension for VS Code. In it, the command-line flags from yesterday do not parse as expected. Instead, the controls you’d want live in the extension’s own GUI settings page.
How to Skip All Claude Code Permission Prompts
In a more closely controlled environment with less risk, say, in a home lab of an enthusiast, the risk of Claude Code accidentally wiping the drive or destroying another repo is minimal. Not that it cannot happen, but a reasonable amount of backup or git versioning practice could mitigate most of the risks from accidental or non-malicious actions. In such a scenario, Claude asking for permissions only slows down making your idea come true.