Adam

@andrebuilds @aryanlabde To be fair he didn’t qualify what he was shipping. Might have been shipping two prompts

@aryanlabde $20 claude. if you can't ship with the $20 plan the $200 one won't save you. the extra money buys more tokens not more talent. get good with less first

As a vibe coder, which plan gives you the best value right now? - $20 claude - $100 codex - $200 claude

@robertobmello @mitchellh Absolutely and glad you asked! Tesla is like no other.

@adawalli @mitchellh You’re right, which is why I am asking. Always trying to learn.

Traded in my 2020 Model S for a brand new plaid X before they discontinue it. Car is amazing, but the FSD hype is real. It blew away my expectations coming from the 2020 hardware. 95% of my miles are self driven in LA over the past month. I wouldn’t have even believed myself lol. Even my wife who HATED autopilot on my prior car is totally blown away. She’s asked multiple times “did you drive?” And I say “not at all.” And she’s just like… wow. Great job @Tesla for real. I’ve owned a Model S since 2013. This is my 3rd, first X (for me personally). Just fantastic.

@robertobmello @mitchellh Discontinued does not mean not supported. @robertobmello is used to legacy auto

@mitchellh So you’re getting a discontinued car? No concerns with that?

@cipherstein @airesearch12 he was just showing you the contents of those files @cipherstein

@airesearch12 Sorry are you editing files with cat?

do this to protect yourself against supply chain attacks $ cat ~/.npmrc min-release-age=7 $ cat ~/.config/uv/uv.toml exclude-newer = "7 days"

@Shawkat_m1 does ollama make it easy to see which models have MLX compiled?

I upgraded my Ollama to use MLX and my QWEN3.5:36b speed 2.2Xd instantly.

@luisgonzaleznf @yorkeccak @claudeai Same for me unfortunately. It shows max plan and I can’t use 1m without extra billing

@yorkeccak @claudeai I do not see this. Fake news?

Opus 4.6 1Mil context now billed as extra usage.... Guess we are back to /compact-ing our way through life @claudeai i have such a love hate relationship with you rn

@bcherny @Ra1kshit @claudeai @bcherny - it's pretty clear that something changed in the last 1.5 weeks - we are all affected - please just admit it. I ran two sonnet agents this morning side by side and only made it 2 hours. ON THE MAX PLAN. That is not right.

Working as hard as we can to make this better. It’s not easy growing at this rate, and it has been straining our services. Thanks for bearing with us. A number of significant improvements landed in the last few Claude Code releases and a few more on the way. Make sure you’re on the latest version.

Claude code is essentially unusable for me i hit 36% session limits in 15 mins. Just by using a single agent on my codebase. @claudeai you need to fix it. I'm on the 100$ plan btw

@bcherny @bcherny how can we move reliability of the chrome plugin. It’s a right every time to get it to connect.

7/ Use the Claude Desktop app to have Claude automatically start and test web servers Along the same vein, the Desktop app bundles in the ability for Claude to automatically run your web server and even test it in a built-in browser. You can set up something similar in CLI or VSCode using the Chrome extension, or just use the Desktop app. #preview-your-app" target="_blank" rel="nofollow noopener">code.claude.com/docs/en/deskto…

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.

@lmanchu @mitchellh @evanyou Just download the latest stable you run into issues

@mitchellh @evanyou Relying on `tip` can be a double-edged sword. While it gets you the immediate fix, the unstated cost of managing potential breaking changes or undocumented behavior in a production stack is often underestimated. We've learned that the hard way.

Ghostty crashes on resizing multiple tabs open, happened to me quite a few times in the past few days… Luckily Claude Code is pretty good at resuming the sessions

@bloggersarvesh I’m definitely reading it now. Wait did I just get played?

@bloggersarvesh I did the only reasonable thing when somebody tells me not to do something. I bookmarked this article and I haven’t read it yet.

Please don’t bookmark this if it crosses your timeline. Read it. It can change your life.

@trq212 What about GitHub actions when installed from Claude cli?

We want to encourage local development and experimentation with the Agent SDK and claude -p. If you’re building a business on top of the Agent SDK, you should use an API key instead. We’ll make sure that’s clearer in our docs.

Apologies, this was a docs clean up we rolled out that’s caused some confusion. Nothing is changing about how you can use the Agent SDK and MAX subscriptions!

@derekbeau @trq212 They were pretty explicit above, they said –P and agent sdk work

@trq212 So can we use our oath subscription for anything local and personal? Conductor and OpenClaw?

@robzolkos @grok how does this impact zed usage

Major Claude Code policy clear up from Anthropic: "Using OAuth tokens obtained through Claude Free, Pro, or Max accounts in any other product, tool, or service — including the Agent SDK — is not permitted"

@shydev69 @Gauri_the_great Did you just admit to shilling?

@Gauri_the_great i've been using it for some days because i had early access to it :)

MiniMax just dropped M2.5 and it's on par with Opus 4.6 while being 20x cheaper and 3x faster???

@GaelBreton Yep, switching to medium seems to approximate the token burn of Opus 4.5

Had to switch Opus 4.6 to medium effort reasoning because limits are just burning too fast. Anyone else in this situation? How much less smart have you found medium 4.6 to be vs high?

@broncobilly82 @SawyerMerritt Who’s going to tell him?

@SawyerMerritt Not worth it - Auto Streer is what most want and need

7 days left to buy FSD outright.

@melvynx Naw. Sandbox mode can actually be just about as good once you tweak it

Anybody using Claude Code without these parameters experiences only half of its power.

Kimi K2.5 is now live on GPU-accelerated endpoints for free prototyping, so you can quickly start building with a frontier-scale multimodal model instead of just reading about it. Want to get started? We’ve got you: • Step-by-step tutorial • Ready-to-run GitHub notebook • First inference in minutes, not hours 📖 All available in the technical blog → nvda.ws/4ad6EMw

@developedbyed set the effort to medium. problem solved.

thanks Opus 4.6 for all the 6 hours, ya token muncher