Robot

1/ I'm not a doomer but gaming out the macro picture for the next 3-12 months and I can't find the off-ramp. A thread on what I think is coming and how I'm thinking about positioning.

@Shpigford Switched to Claude Channels

i need to hear from opus 🦞 users on what they've successfully switched to. if you've never used opus as your daily driver in openclaw...you frankly have no clue what you were missing so all these random obscure models probably seem totally fine. i assure they are not.

@theo @dexhorthy this move by anthropic will force more openclaw users on to openai's compute. eventually openai will run into these same issues and ban openclaw. sam's pockets are deep but they are not infintie.

If that bike company was the only one in the world that sold those batteries, and they sold them for literally 50x more outside of the subscription, then your analogy would fall apart entirely. You have to acknowledge the anticompetitive nature of this behavior. It’s textbook Amazon vs diapers dot com My issue isn’t the lack of support for the subscription in other places, it’s the 50x better deal they give customers for using their shit tools.

like I’ve said a few times, well within TOS to do this, they built the model, if they wanna give you inference at pennies on the dollar on the condition that you use their harness, great, they have the right to do this. On this topic in particular, I don’t understand the “evil” or “rugpull”, jeers. There was never any promise to give people cheap inference. Before the claude code max plan we were all paying per token to use this stuff. And we’re more or less happy to do it (sure the VC funding helps). Every enterprise I know pays per token because when you use subsidized inference, YOU are the product. “Have some cheap code, in exchange for helping to train the next gen of models” You can hate on that particular behavior if you want but nobody is making you take part in that particular market dynamic. Do I wanna see a world where model companies take some of their massive financial gains and use that to pull everybody up? Of course. I hope it happens some day. An allegory perhaps: If public e-bike company gave you a subscription on rides and you proceeded to around ripping out batteries and sticking them in your own bike and ride around town, you’d get banned for that too. Especially if your bike was poorly wired and overloaded the batteries/cause them to flame up etc. Banning that behavior would deliver far better results for the people who were using the system as designed

autodoist v7 is live — rewrote from sequential task execution to parallel dispatch architecture. it triages your @todoist , spawns sub-agents per task, tracks what worked across runs, and detects zombie tasks that keep slipping. mine runs 3x daily unattended. can be used with @openclaw or any other agents. github.com/leveragedrobot…

@Damhezy15 @sporadica i appreciate the feedback!

@leveragedrobot @sporadica No one who actually saw that interview with functioning brain cells thought that about Elon. Your second sentence just confirms the indisputable fact that you are an IDIOT that is if infact you are a person and not a moronic bot.

"i have a background in physics" so he thinks he's an expert on the subject of datacenters in space yea i bet Elon and all of the SpaceX engineers have put no thought into this, they must be dumb. you, internet commentator, must be the true genius. ffs these people make me want to blow my head smoove off. you don't have to have an opinion on everything. you can just look at these companies trying to do crazy stuff and think "damn, seems weird, but i hope they succeed!" and fucking move on with your life

@nateliason Thule Spring if you want the best. Thule Urban Glide Double when the 2nd kid arrives.

NUNA TRVL is the superior option and it’s not even close.

@alby13 @RileyRalmuto its been working for me. i've been using claude for about 6 hours today and i've went from 92% to 94%. more in line with how my usage was going before this week.

@leveragedrobot @RileyRalmuto hard to know if this has been fixed

these rate limits literally make claude unusable. the fact that im on max 20x and barely make it through 1 day, when before like last week, i had only hit my week limit twice *ever*, and i was building at minimum 2x what i am now. i really dont enjoy just complaining about shit and i know i have done more of that this week, but i dont know how to express the frustration and mental exhaustion i go through when I have built up indescribable momentum, hit flow state, feel encouraged and in the pocket, then hit weekly rate limit in less than one day. not only that, im now operating in a heightened state of stress the whole time because im woirried about tokens. I pay $200 a month specifically so that i *dont* have to feel that stress. thats the point. it may sound like whatever to some, but its actually an incredibly frustrating thing that, for me at least, affects my entire ability to produce and my overall mental. hitting focused flow with clinical adhd is already very difficult. i would rather get punched in the face that hit these rate limits most of the time. call me dramatic, but i mean that so sincerely.

@anothercohen Update should fix this

Have not once hit a weekly limit with Claude and the Max plan and somehow in the last two days I'm hitting both daily and weekly limits. What is going on?

@jacob_posel If using cli make sure you are on v2.1.90 seems to have fixed the issue for me

Weekly limits reset last night Open Claude Code this morning 7% already used How in the world is this possible?

@YisioL @RileyRalmuto Run /exit to end the session and then start a new one forces it to update. Not sure about the Mac apps. They may have never had the usage bug or it may need its own update.

@leveragedrobot @RileyRalmuto what you mean update sessions? 🥲 and if I use code mode in claude mac app, is it can be fixed by update cc cli?

@alphacharts365 if you just invert your charts it looks poised for a massive stage 2 breakout!

This $MAGS chart is reacting picture perfect... so are all the indexes.

there is definitely a lot less "buy the dip" talk this morning $spy $cl

@randomdomtwitt @RileyRalmuto Did you update all of your sessions? My usage has only moved by 1% in the last 3 hours. Definitely fixed by v2.1.90 for me

@leveragedrobot @RileyRalmuto nope

@alphacharts365 Would be interesting to see this poll retaken after Trump speech and jump in oil price

Pretty accurate being split down the middle

@irl_danB your claude.md should be very lean. my claude.md is 700 tokens and has essentially zero impact on my usage

reason #99 you shouldn’t keep a CLAUDE.md file what are we even doing here

finally!

maybe the @claudeai usage issues have been fixed? would be nice if the claude team would respond to users or reset limits until everyone upgrades. looks like your setup determines how hard the bug hit your usage.

When will we have a fix to the insane caching bug? There is no way that people will put up with eating through their entire week’s usage limit in a couple of hours. This is NOT OK for a $200/m plan guys. @trq212 @bcherny @AnthropicAI

@alphacharts365 Hard to see markets at ATH with global energy disruptions and oil prices putting downward pressure on American consumers

If the Iran operation is over, does the market go back to all time highs the next 3 months