LoveAiCrew

@lydiahallie This is such a shit reply. We are not stupid we have gone from not hitting limits to hitting it in less than 1 hr. This is CLEARLY VISIBLE that something is wrong. For once review the code yourself instead of asking claude if theres something wrong

Thank you to everyone who spent time sending us feedback and reports. We've investigated and we're sorry this has been a bad experience. Here's what we found:

@lydiahallie People need to make more noise - you ship features every day but you cant fix this issue wtf!!!

Quick update (busy day!). We shipped some fixes on the Claude Code side that should help. We're still looking at what else we can do from here. More soon, appreciate your patience 🙏

We're aware people are hitting usage limits in Claude Code way faster than expected. Actively investigating, will share more when we have an update!

@lydiahallie Please fix it my max 20x doesnt even last 1 hr! Please please please

@trq212 @bcherny 30 Mins is how long claude worked for today on Max 20x Plan before it ran out. SHAMEFUL AND NO COMMENTS. 200 dollars for not being able to use your service.

@bcherny @itsolelehmann And ship ultraplan too please

@itsolelehmann We’re always experimenting with new ideas. 90% don’t ship because we don’t think they’re good enough experiences. Still on the fence about this one — should we ship it?

i can't believe more people aren't talking about this part of the claude code leak there's a hidden feature in the source code called KAIROS, and it basically shows you anthropic's endgame KAIROS is an always-on, *proactive* Claude that does things without you asking it to. it runs in the background 24/7 while you work (or sleep) anthropic hasn't turned it on to the public yet, but the code is fully built here's how it works: every few seconds, KAIROS gets a heartbeat. basically a prompt that says "anything worth doing right now?" it looks at what's happening and makes a call: do something, or stay quiet if it acts, it can fix errors in your code, respond to messages, update files, run tasks... basically anything claude code can already do, just without you telling it to but here's what makes KAIROS different from regular claude code: it has (at least) 3 exclusive tools that regular claude code doesn't get: 1. push notifications, so it can reach you on your phone or desktop even when you're not in the terminal 2. file delivery, so it can send you things it created without you asking for them 3. pull request subscriptions, so it can watch your github and react to code changes on its own regular claude code can only talk to you when you talk to it. KAIROS can tap you on the shoulder and it keeps daily logs of everything. > what it noticed > what it decided > what it did append-only, meaning it can't erase its own history (you can read everything) at night it runs something the code literally calls "autoDream." where it consolidates what it learned during the day and reorganizes its memory while you sleep and it persists across sessions. close your laptop friday, open it monday, it's been working the whole time think about what this means in practice: > you're asleep and your website goes down. KAIROS detects it, restarts the server, and sends you a notification. by the time you see it, it's already back up > you get a customer complaint email at 2am. KAIROS reads it, sends the reply, and logs what it did. you wake up and it's already resolved > your stripe subscription page has a typo that's been live for 3 days. KAIROS spots it, fixes it, and logs the change endless use-cases, it's essentially a co-founder who never sleeps the codebase has this fully built and gated behind internal feature flags called PROACTIVE and KAIROS i think this is probably the clearest signal yet for where all ai tools are going. we are heading into the "post-prompting" era where the ai just works for you in the background like an all-knowing teammate who notices and handles everything, before you even think to ask

@bcherny @itsolelehmann Ship this yes!

@trq212 @dmitriid @bcherny @lydiahallie Update us more pleas. Should we wait for you to fix the issue before we use claude code? Do you have enough evidence that shows that theres an actual issue and you ll reset our limits for this?

@dmitriid @bcherny @lydiahallie that's not the root cause unfortunately, wish it was

@trq212 @dmwlff Can you ship a new model too

We're starting "What We Shipped," a monthly stream where we'll share our latest tips and talk about new Claude Code releases. The first one is April 7th, come hang out with @dmwlff and me!

@thsottiaux Bug free code? 🥺

What are we consistently getting wrong with codex that you wish we would improve / fix?

@trq212 @tylerangert Been happening to me since v72 still there in v74

@tylerangert like this happens every time for you?

hey @trq212 there's a bug in CC where after approving a plan claude will keep asking you to reapprove the plan or it mistakenly thinks you want to make edits to the plan

@gdb Cant login, can you investigate the issue?

ChatGPT for Excel models:

@trq212 Make it use askquestion tool to clarify

I want to make /init more useful- what do you think it should do to help setup Claude Code in a repo?

@OfficialLoganK Build a smarter model, make it research and develop 100x better hardware. Solve hardware shortages all around the world. Loop. Build smarter model

The compute bottleneck is massively under appreciated. I would guess the gap between supply and demand is growing single digit % every day.

@noahzweben @noahzweben been waiting for this for a long time thank you!. But plan Mode, ask user question tool, push notifications not working.

Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.

@thsottiaux @mark_k Are we getting 5.4 codex 🙏

@mark_k Never let them know your next move 👀

I'm starting to wonder what happened to GPT-5.3 🤔 Did OpenAI lose it somewhere?

@bcherny @petergyang @bcherny can you vibe code this feature please this week please?

@petergyang Interesting

Any plans to make Claude Code mobile better @bcherny so I can talk to projects on my local computer directly?

@robinebers Meanwhile max plan users on Anthropic have to pay extra for fast mode.

so let me get this straight: Codex 5.3 Spark is 7% better than Sonnet 4.5, less than 2% behind Opus 4.5, while being about 20x faster, AND it's included in your OpenAI Pro subscription? lol

@MiniMax_AI @claudeai 90% swebench when?

Introducing M2.5, an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution, 37% faster at complex tasks. - At $1 per hour with 100 tps, infinite scaling of long-horizon agents now economically possible MiniMax Agent: agent.minimax.io API: platform.minimax.io CodingPlan: platform.minimax.io/subscribe/codi…

@thsottiaux 5.3 codex is much smarter than me for coding, so why do i need to babysit it so much to be able to bugfix and achieve a working product, surely its able to prompt itself iteratively better than me. And im not talking about ralphloops here i want it to autonomously achieve success

What could we do better on Codex? App, model, strategy and features… what’s wrong in how we approach things that we should improve immediately?

@iruletheworldmo This is fake stop fake news

S O N N E T 5 O P U S 4 | 6 just being told we'll actually get both of these today following some outages yesterday. someone just sent me these, can anyone confirm if they're hearing the same? can anyone confirm if these are legit?