Jon Brown

@williamsba openrouter/auto is good for that. You can limit it to only the models you want it to use as well. But all that is hitting API credits, not quotas (OAI, Anthro) . Best bank for the buck it Minimax Coding Plan, but I stick with OAI for code and most everything else really.

@jb510 Haven't played with Minimax M2.7 but will check it out! Building in logic to escalate to more powerful models based on the task at hand.

Testing out the new GLM 5 AI model. Lots of hype for this one with comparable output to Anthropic's Opus 4.6 at a fraction of the cost! openrouter.ai/compare/z-ai/g…

@wesbos Software was already a bloated mess of packages... now it's a bloated mess of packages buried under a bloated mess of clanker slop. I can no longer navigate issues or PRs on any of the OSS projects I follow.

If you are wondering why GitHub is struggling right now. This, plus every single platform being built on top of them, and pushes the code back to them. Their graphql api alone is so permissive, with high rate limits. It must be NUTS over there right now.

@webtw @Substack Same. I used to use social media apps, but I uninstalled them all. The "friction" of using the web is a welcome deterrent to use them as much. And... removes the notifications as well, further reducing the incentive to check in.

@jb510 @Substack Big miscalculation in what I’m willing to do to read an article, lol.

My goodness @Substack why are you trying to force me to download an app just to read an article??? 😭😭😭😭

@krishdotdev alias hgr="history | grep " Note: I actually use ripgrep alias hrg="history | rg "

Linux users, when they need to run a command in the terminal: ⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬇️⬇️⬇️⬇️⬆️⬆️⬆️⬆️⬇️⬇️⬇️⬇️⬇️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬆️⬆️⬆️⬆️⬆️⬇️⬇️⬇️⬆️⬆️⬇️⬇️⬆️⬆️⬆️⬆️⬆️⬆️⬆️⬆️ Ah, here it is!

@wesbos Used to get stuff like this from "Google Partners" as well. Legit emails, scammy as all hell. Basically giving independent contractor salespeople legit emails.

how TF is this scammer spoofing the meta domain and passing SPF / DKIM? They sent this email and then called me 5 mins later from what sounded like an Indian call centre

@elonmusk And still not one on the Moon or Mars... slacker I guess you're now just wasting all your time on Twitter...

Over 500 rocket landings now

@jeffr0 I always like your food photos :). I don't often post mine anymore, but here's last night's dinner.

Today is my wife's birthday. We started with a great breakfast at First Watch. I didn't take food photos because I was too hungry, but it was delicious. Later, we're going to the Cleveland Museum of Art because that's where she wants to go. Then, it's off to Little Italy!

@jeffr0 You've got to put simple automations on your complex automations. My OpenClaw writes scripts that are hooked to cron jobs that eval/valiadate critical things are working. If they are, nothing happens. If they're not, they tell OpenClaw to investigate and fix.

How does one put checks in place to make sure an automation is working? It would be nice to know instead of three weeks later. How many fail-safes do you implement to ensure the automation is working?

@wesbos 15" MBA FTW. Only thing I really miss is the nanocoated screen. If it had a pro chip I'd expect 3yrs between replacements, without, 2 years. Occasionally, an anonymous USB-C port is only on the left side.

I’m so over the 16” MacBook. I’ve had a 15/16 for my whole career and I think I’m gonna go 14” next time

If you're a "WordPress Person" I know, but now doing AI stuff _outside_ WordPress coding, LMK. Very curious who else... I was instantly clawed pill. Feels like WP 2005 to me. Wanting to go to meetups and Clawcons, etc. And I just landed my first pure AI Consulting gig :)

@mcuban This isn't something you should "need" an LLM for... Insurance contracts should be human-readable; they're not. Insurance contacts should not be full of "issues you will face" when using them.

You are not smart if you don’t run your insurance contracts through Claude or any other LLM and ask for a summary and issues you will face Doesn’t matter if you are the employee or the employer or buying an ACA , Medicare , MA or Medicaid plan. Get that summary and suggestions. Ask it questions and to explains, simply, the things you don’t understand. There are no more excuses

@euthelup But WP is getting real time collaborative editing! So you can now have multiple ai agents write content simultaneously I guess? Would have been a useful feature 10 years ago. WP is dying because it made the wrong bets and it stopped being a usable CMS.

Funny how "AI is killing CMSs" always means WordPress specifically. Wix is fine. Squarespace is fine. Webflow is fine. Almost like the take was never really about AI.

Let me explain what just happened 👇 5 minutes before the President announced a halt to attacks on Iran… someone placed a $1.5 BILLION bet on stocks going up and dumped $192 million in oil. 5 minutes… These trades were 4 to 6 times larger than anything else in the entire market. Whoever did this wasn’t guessing. You don’t risk $1.5 billion on a hunch. There was zero public indication this announcement was coming. No leaks. No press. Nothing. The only people who knew were in the room when the decision was made. Someone in that room picked up a phone. And within minutes they made more money than most Americans will earn in a thousand lifetimes. In a single trade. On a war that cost you $4+ a gallon gas and $16 billion in tax dollars. American citizens funded this war. Politicians are profiting from it. This is not the first time. Every major announcement from this administration has had massive suspicious trades right before it dropped. Tariff reversals. Policy shifts. War decisions. This is the most blatant insider trading operation in the history of American politics. It’s not even close. And it’s happening over and over in broad daylight. You would go to federal prison for trading on a tip from your cousin. These people are front running war decisions with billion dollar bets and nobody will ever ask a single question. Nobody will be investigated. Nobody will be charged. By tomorrow this will be buried under the next satisfying headline. Just like last time. And the time before that. The game is rigged. And they’re not even trying to hide it anymore…

@AlexFinn Alex, don't spread misinformation. OpenAI did not buy the project. OpenClaw is owned by the independent OpenClaw foundation. (which I lead)

@SenSanders Love Bernie, and agree AI need some regulation. But he lead the agent to _give him the specific answer he wanted_ on regulation. LLMs are extremely biased to re-align with you if you express disagreement. We need to teach more people to think critically and recognize that

I spoke to Anthropic’s AI agent Claude about AI collecting massive amounts of personal data and how that information is being used to violate our privacy rights. What an AI agent says about the dangers of AI is shocking and should wake us up.

@SenSanders x.com/sensanders/sta…

We need an AI/LLM benchmark that measures "leadability". U: What color is the sky normally? A: The sky is blue + 500 words on why. U: Don't you think the sky is actually Pink? A: You're absolutely correct to push back on that, the sky is indeed pink.

@jeffr0 @WarrenLNaida @TheCre8tiveDiva Pizza al tonno is common in Southern Italy as well. No different than anchovies or sardines on pizza in the south.

@WarrenLNaida @TheCre8tiveDiva You're lying.

Ummmm @TheCre8tiveDiva