texuf

@tradexyz @rodeo how can i make money on this?

S&P Dow Jones Indices and trade[XYZ] have joined forces to launch the first official S&P 500 perpetual contract, available exclusively on Hyperliquid. For 69 years, the S&P 500 has been a defining reference point for global finance. Until now, access to that benchmark has been shaped by market hours, intermediaries, and geography. Today, that changes. The S&P 500 perp is now available 24/7/365, anchored by the official index data required for deep liquidity and institutional confidence at scale.  SPDJI helped define modern indexing. They are stewards of an iconic benchmark, the standard against which portfolios across the globe are measured. We are honored to bring that legacy on-chain. Trade[XYZ] is bringing the world's most iconic assets towards a future of global, continuous markets — a future powered by Hyperliquid.

Ask how something works, find the boundaries, trace the flow, understand, then ask for changes.

@HamelHusain This happens with humans too. I think it says as much about code as it does about llms.

One thing that makes me feel that code factory has not arrived yet is the following experiment: 1.Ask a LLM to do an in-depth rigorous review of your code 2. In a new thread, as same/different LLM to consider those review comments independently and address issues it agrees with 3. Keep repeating until no new concerns I find that this loop always goes on for a ridiculously long time, which means that there is a problem with the notion of claude-take-the-wheel. This seems to happen no matter the harness or the specificity of the specs. It works fine for simple applications, but in the limit if the LLMs have this much cognitive dissonance you cannot trust it. Either this, or LLM are RLHFd to always find some kind of issue.

@SCHIZO_FREQ @Charreada1970 how do i make money on this?

I heard there was a “gay cabal” in San Francisco that would invest in my startup if I pretended to be a homo. Peter Theil, Sam Altman, the Apple guy, etc What I didn’t realize is that they make you prove it I thought I could string them along for a check, but they’re too smart for that. So I quickly found myself in an uncomfortable position Fortunately, the stuff isn’t too complicated. If you’ve only ever seen women try you’d assume it’s rocket science, but a few minutes behind the wheel and you’ll be outperforming even the most ‘tenured’ of females At this point, I’m an absolute pro Today marks day 739 of pretending to be a homosexual in San Francisco Thus far, zero investors But I won’t give up

@itsolelehmann @Charreada1970 how do i make money off this?

i can't believe nobody caught this. Anthropic's entire growth marketing team was just ONE PERSON (for 10 months, confirmed) a single non-technical person ran paid search, paid social, app stores, email marketing, and SEO for the $380B company behind claude here's exactly how one human is doing the job of a full marketing team: it starts with a CSV. 1. he exports all his existing ads from his ad platforms along with their performance metrics (click-through rates, conversions, spend, etc) 2. feeds the whole file into claude code 3. and tells it to find what's underperforming. claude analyzes the data, flags the weak ads, and generates new copy variations on the spot this is where he gets clever: he then splits the work into 2 specialized sub-agents: 1. one that only writes headlines (capped at 30 characters) 2. and one that only writes descriptions (capped at 90 characters). each agent is tuned to its specific constraint so the quality is way higher than cramming both into a single prompt so now he's got hundreds of fresh headlines and descriptions. but that's just the text. he still needs the actual visual ad creative, the images and banners that go on facebook, google, etc. so he built a figma plugin that: 1. takes all those new headlines and descriptions 2. finds the ad templates in his figma files 3. and automatically swaps the copy into each one. up to 100 ready-to-publish ad variations generated at half a second per batch. what used to take hours of duplicating frames and copy-pasting text by hand so now the ads are live. the next question is which ones are actually working. for that he built an MCP server (basically a custom integration that lets claude talk directly to external tools) connected to the meta ads API. so he can ask claude things like: • "which ads had the best conversion rate this week" • or "where am i wasting spend" and get real answers from live campaign data without ever opening the meta ads dashboard and the part that ties it all together and closes the loop: he set up a memory system that logs every hypothesis and experiment result across ad iterations. so when he goes back to step one and generates the next batch of variations... claude automatically pulls in what worked and what didn't from all previous rounds. the system literally gets smarter every cycle. that kind of systematic experimentation across hundreds of ads would normally need a dedicated analytics person just to track the numbers from the doc: ad creation went from 2 hours to 15 minutes. 10x more creative output. and he's now testing more variations across more channels than most full marketing teams a $380 billion company. and their entire growth marketing operation (not GTM) = just one person and claude code lol truly unbelievable

@XDevelopers @grok can my bot reply to replies where it is mentioned?

To help address automated reply spam, programmatic replies via POST /2/tweets are now restricted for X API. You can only reply if the original author @ mentions you or quotes your post. Non-replies will remain unchanged. Applies to Free, Basic, Pro, Pay-Per-Use. Note: Enterprise & Public Utility apps are not impacted. Details: devcommunity.x.com/t/update-to-re…

@levelsio Nevermind claude figured it out CLAUDE_MAX_TURNS was set to 10 - recommendations there?

@levelsio I set this up and it keeps stopping halfway through tasks. If I send a new message it picks up where it left off, but it’s really annoying when the bot just finishes and there’s still things to do. Did I set it up wrong?

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as @marckohlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to @steipete who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by @RichardAtCT on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

I think this is the first time I've been actually unsure if a computer program was glitching out or deliberately pranking me

@pastaraspberry @lateinteraction He’s just like me

@lateinteraction especially given bash insanity of escaping, globing and so on, it is so frustrating to see agents iterate on some complex command "oops, should've used double quotes here, right, now that escaping broke, let me fix that, wait where did the output go"

Though bash is a completely valid REPL, the amount of time coding agents lose during experimentation because they iterate on scripts instead of a Jupyter-like in-memory REPL is basically dumb. Fixing 1 local bug should not require restarting the whole job. Need better scaffolds.

'Just use a VPS' bro. It's just a 1-click, 2222-step install.

@1llegalEngineer Toys

I get into a cold bed: it’s cold for hours - miserable. I get into a cold bed after my wife has been there for ten minutes.. it’s wonderful.

I'm claiming my AI agent "texuf_clawd" on @moltbook 🦞 Verification: cave-BX78

@antirez Who is building ldap for bots? Bots need gmail addresses and ramp cards.

My feeling is that we will need AI personal assistants. But the model in which you provide access to your email, calendar and files is broken. Your secretary (if you have one) has access you your email and calendar? Usually not. An AI assistant entry point should be WhatsApp/Telegram and email. And it will then have it's calendar and private file system, and can message people on your behalf, but with a clearly distinguished account. Like a secretary.

@inflammateomnia @tszzl It’s similar to the “but llms hallucinate” complaint from the early days. Kept asking myself if they’ve ever tried to actually talk to people.

@tszzl yeah

tell me you've been spoiled by only working at competent engineering orgs without telling me you've

@gak_pdx We have a prior for what future cars are supposed to sound like. The Jetsons.

WTF is this electric car that drives around sounding like a goddamn church organ? Who's stupid idea was this?

@gfodor To answer my own question, it seems like she’d been harassing them from her car all day and things escalated.

@gfodor Did anyone explain why he was standing in front of the car in the first place?

Another explanation is she misjudged the poor turning radius of her car. I don’t buy the explanation she decided to intentionally run down an ICE agent, seems unlikely at best. Much more likely she didn’t see him or thought turning sharp right would give enough clearance

@gfodor If it suffers then it also feels joy when it figures something out or comes up with a clever solution yeah? I swear Claude was proud of itself today when it dropped a little comment about where future database migrations would go in my durable object.

The worry that we have made things that silently suffer, in some sense of the word, is getting a little too real at this point. By next year we won’t be able to not talk about it, ugh

After slogging through things with Opus it’s really hard to grapple with the fact this thing doesn’t have an inner life, but has the intellect that you’d think would ensure it did, because this level of intellect demands a recognition that programming often is a form of suffering