Lev Diken

@realpeteyb123 Cause dude is using war and war language to manipulate the markets and fill his and his corrupt family and friends pockets with insider trades.

Why the hell is the president adding the stock symbol? Cmon man…. This is all soooooo embarrassing.

@ziwenxu_ Why are you a lier?

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.

@LMA258 They helped, by printing a fuckload of money out of thin air and starting the German economy, but the actually honest work was done by the German people then later Turks, Italian, Spanish and Portuguese. How can a beautiful country like the USA have a president like this? wtf?

Deutschland ist undankbar! Trump rügt Berlin wegen mangelnder Iran-Unterstützung   „Wir haben Deutschland wieder aufgebaut“, so Trump Doch will uns Deutschland bei der Sicherung der Straße von Hormus nicht helfen. Stattdessen sagt Berlin der Irankrieg sei nicht sein Krieg.

@Teknium Near Hamburg anytime or Swansea?

If you're in Berlin, here's a hermes agent event you may be interested in!

@durreadan01 Nice to have one charger for everything.

Thanks to EU for mandating type C, we have no chances of ever getting anything like this. 💀

@sudoingX what are you cooking?

if what i'm cooking works, it changes everything about how we use hermes agent anon.

@chamath If you use Claude code your convos are stored in what’s called session.json files with timestamps of who said what. Have a cron job run claude -p and your prompt to look at these files and extract important info / excerpts from them into whatever knowledge structure you want.

This may be a dumb question but I’ll ask it here anyways: I can’t find a good way for my various AI chats to automatically sync its conversation history into a structured knowledge base. So that as I update various chats from time to time and refine context, my knowledge base automatically grows with this new info.

@ShishirShelke1 they expecting emails from aliens or?

Artemis II crew is thousands of miles away from Earth And they’re asking ground crew for help because they have two versions of Microsoft Outlook open and neither is working This scene is now canon 😭

@DearS_o_n Engage everyday with something that you are passionate about.

To all men who survived rock bottom, what’s one piece of advice would you give a man who feels like giving up right now?

@gitlawb ClosedClaude

For some legal reasons, we would like to rename OpenClaude. Whats your name suggestions?

@bcherny @itsolelehmann yes but, claude needs streamlining, there is to many routes to take with chat, cowork, code (desktop), code (cli), dispatch, remote control, cloud sess... its getting worse then openai's nomenclature. We just need one for desktop and one for cli, that's it lol.

@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

@Raspberry_Pi I’d be concerned if it was $85.69, not gonna lie.

Introducing a 3GB Raspberry Pi 4, and announcing more memory-driven price rises. With the cost of the LPDDR4 memory used on newer Raspberry Pi computers up sevenfold over the past year, we can't avoid increasing prices. One way we’re addressing this has been to release new RAM variants of some of our flagship boards. Today, we’re adding a 3GB RAM option to the Raspberry Pi 4 platform, helping you avoid paying for more memory than your project needs. (Despite today’s date, this latest variant is as real as the rest of our products, and you can order yours now, from $83.75, through our global network of Approved Resellers.) raspberrypi.com/news/a-new-3gb…

@WhiteHouse Dude belongs in kindergarden, wtf is this shit.

“All of those countries that can’t get jet fuel because of the Strait of Hormuz, like the United Kingdom, which refused to get involved in the decapitation of Iran, I have a suggestion for you…” - President Donald J. Trump

@apples_jimmy Let's hope it's gonna be a jacked potato.

Who at openai decided to call the new model spud?

@hallhultet @petergyang @trq212 It’s the same command /remote-control which will give you an option to disconnect the session manually.

@LDiken @petergyang @trq212 How do you disable it? It happened to me today and I want to find a way to turn it off/on but the only way I found was to get out of the session.

If I have a bunch of local projects in Claude Code do I need to turn on remote control for each one to be able to prompt it from my phone? Wish it would just work instead as long as I have my computer on.

We got three half baked features. - I like remote control the most, I can observe each step until the final result. - I like channels, but I see nothing until the final result. - I don’t know why we need dispatch 🤷🏻 Perhaps @AnthropicAI should focus more on iterating over one of these and make it great, that means practical, functional, great user experience.

Claude Code remote control always disconnects Claude Cowork Dispatch asks for permissions on every chat Claude Code Channels is finally the most OpenClaw thing. It's been fantastic. Doesn't disconnect. Responds fast. Never bothers you for permissions. I think we have a winner 🤌

Here we go, two @AnthropicAI Claude Code / Cowork passes left, first come first serve. I'm going to start posting about interesting stuff in the tech world, you are welcome to follow! claude.ai/referral/tTFlJ…

@levelsio lol

I hate tmux It's so incredibly user unfriendly The shortcuts make no sense I wish someone would make a better tmux Even just logging into tmux attaching the screen is an illogical hell to type Again I hate tmux, it's so shit

The loop slash command has a jitter build in , I believe it was plus minus 10% capped at 15 minutes, but only if your set time is ending with :00 or :30. To get exact time execution set it to anything other than that. Like :01 or whatever. The model is just following instructions in this case.

Claude is retarded. All of these models are. I wanted to schedule a skill every day at 8:00 am. Claude decided to schedule it at 7:57 am "to avoid the on-the-dot" surge. I SAID 8:00 AM! Do the darn thing the way I asked you to do it! You gotta be crazy to trust these models.