Same is now happening to Bitwarden, enshittification is accelerating, now good programs don't even last two years.

GPT-5.x in general are very disappointing, the only good chat model was GPT-5 in the first week before they made "the personality warmer" and Codex in general was always kinda meh.

Irrelevant to most ordinary people in the sense that few directly use it, but popular with the source of much of our discourse / culture. Think journalists, taste makers, meme creators etc.

Why do I have to manually switch between medium, high, extra high?? This is comedy at this point, Claude Code "just works" without having to think about obscure stuff like this and it still produces a better output. OpenAI is just embarassing at this point, ChatGPT also got ruined with gpt-5.2 which talks and has the brain of a 2 year old, even gpt-3.5-turbo was better. Did they still have no successful training run?

Claude responds differently to "think", "think hard", and "think very hard". Just because it's hidden to you, doesn't mean a user doesn't have a choice.

Saying gpt-3.5-turbo is better than gpt-5.2 makes me think something you got some of them hidden motives.

https://code.claude.com/docs/en/common-workflows#use-extende...

’’’Phrases like “think”, “think hard”, “ultrathink”, and “think more” are interpreted as regular prompt instructions and don’t allocate thinking tokens.’’’

They dont allocate thinking tokens but they do change model behavior.

I was getting this in my Claude code app, it seems clear to me that they didn’t want users to do that anymore and it was deprecated. https://i.redd.it/jvemmk1wdndg1.jpeg

Thx for the correction. Changed a couple weeks ago. https://decodeclaude.com/ultrathink-deprecated/

Nice blog, this post is interesting: https://decodeclaude.com/compaction-deep-dive/ Didn't know about Microcompaction!

If you're a big context/compaction fan and want another fun fact, did you know that instead of doing regular compaction (prompting the agent to summarize the conversation in a particular way and starting the new conversation with that), Codex passes around a compressed, encrypted object that supposedly preserves the latent space of the previous conversation in the new conversation.

https://openai.com/index/unrolling-the-codex-agent-loop/ https://platform.openai.com/docs/guides/conversation-state#c...

Context management is the new frontier for these labs.

Translations and Image alt texts are useful though.

Always hiliarious when westerners think they know how life works in Russia, China, etc because they heard from it on TV.

Of course it’s all propaganda, comrade, you can openly protest against the ~~war~~ SMO. Don’t forget your Z insignia, though.

Proving me right I see.

>If you really want to stay informed, there are plenty of newspapers, NGOs and other organizations out there reporting the truth.

And they don't report on that kind of stuff because they either support it themselves or are indirectly funded by the government.

So yes, you will need to show your ID which will connect to your account and obviously be used to surveil everything you post online. People on HN of all places need to stop being so naive.

If your theory is that this global push by legislators to introduce age restrictions is actually a secret Trojan horse to harvest government IDs orchestrated by the platform owning capitalists…how do you account for the fact said capitalists have been desperately lobbying against it for years?

>code review

This implies they do any. Every Claude Code release is full of regressions and new features that are released barely work or need hotfixes.

Serving ads and tracking