Daniel Lo Nigro

@bcherny @threadreaderapp unroll

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently. So, here goes.

@getoutline Do you have a comprehensive feature list somewhere? I couldn't find features like this or Mermaid documented anywhere on the site, just in the changelog.

Every Outline workspace now comes with an MCP server built-in, check out more in this weeks changelog: getoutline.com/changelog/mcp

@CreedConfession @MrGoldBro Held hostage? What? If the US government doesn't agree with Anthropic's contract then they can use a different provider. Nobody's being held hostage.

@MrGoldBro Like it or not, Government can't be held hostage by private orgs decisions. This is why we have elected officials.

Let me get this straight: Anthropic refused to work with DoW unless they could promise their tech wasn't used for surveillance or killing. DoW said that they need full capabilities. Anthropic declined to give full access. OpenAI stood by Anthropic for ensuring AI safety. Trump then cancelled all Anthropic usage across the government, including a $200m contract. OpenAI then submits a bid to replace Anthropic.

@987Nabil @thdxr @katyperry You can use it with their web-based chat bot, Claude Code, the Claude desktop app, Claude Cowork, and probably other things. It ends up quite a bit cheaper than API pricing.

@thdxr @katyperry So why does this offer even exist?

done

I'm not so sure about this future where we have CLIs for gambling, and documentation for humans is considered "legacy."

@irabukht Even without AI, there's still major risks to building an entire business on top of another company's product, since the other company might implement your most important features themselves. I'm glad you were able to pivot though!

Toto isn't even the most extreme example: Ajinomoto makes MSG. Their amino acid research produced the insulating substrate in virtually every high-end GPU. 95% global monopoly. In 2021 the chip shortage bottleneck wasn't silicon, it was Ajinomoto's film. Japan holds majority share in 14 critical semiconductor materials. The sintering process that creates a non-porous toilet is the same one that creates a contamination-free wafer chuck. The most critical layer of AI infrastructure is controlled by companies that make toilets, MSG, and window glass.

@WestBlockCapit1 @LowHash @AlexFinn That won't get you local AI though - you'd need to use an AI model through a company like Anthropic (Claude) or OoenAI. You need a lot of VRAM (or unified memory) to run an AI model locally, which is what the Mac Studio provides.

@LowHash @AlexFinn Put it on a virtual server for less than $30 a month

Something big is happening. First Mac Minis. Now Mac Studios. Completely sold out. When I bought 2 Mac Studios a month ago my wait was 14 days. Now the wait is 54 days. The world has changed more in the last month than in the previous 100 years combined. The world's first true AI agent released. Open models became frontier. $10,000 computers started selling out. It is so obvious and clear what is happening on this planet right now. Everyone is going to want personal, private, super intelligent AI assistants sitting on their desk. If you put it in the cloud you are handing all your data and information to corporations. You are being limited by subsidized tokens. You are being surrounded by carefully placed guardrails Within a year compute will be a luxury. Only the early adopters and the mega rich will have access. If you do not have an incredibly deep understanding of OpenClaw, LLMs, and local compute right now, you are on a one way trip to the permanent underclass

@andrii_rom Thanks! I'll try it out when I get some free time.

@Daniel15 github.com/Swetrix/swetri… v5 is live :) would love to hear your feedback if you end up using it!

Very excited to announce that Swetrix v5 is now released 🚀 AI chat, goals, experiments, PoW CAPTCHA, feature flags and A LOT more is released At this point Swetrix is pretty much the best OSS Google Analytics alternative on the market! Learn more: swetrix.com/blog/swetrix-v5

@andrii_rom Thanks! I evaluated Plausible vs Swetrix a while ago (I think it was Swetrix v3), but I'll compare them again once v5 is out!

@Daniel15 Yes, it'll be live this week!

@andrii_rom Are you still planning to release the community edition in January?

It's already live for Swetrix Cloud users. The Community Edition release coming in January 2026!

@zebanderson @MatthewBerman @openclaw @sughanthans1 That and it's always a fixed price per month. No worrying about large bills just because your site/system got popular.

@MatthewBerman @openclaw @sughanthans1 Persistence. Vercel and other serverless cap execution tasks and are more painful. VPS is just raw compute without the time constraints.

Is a separate Mac mini (or computer in general) really necessary for @openclaw ?? If I’m giving my credentials to the different services I use anyways, what’s the difference?

@openclaw @sughanthans1 @MatthewBerman I think the point of the Mac mini is to get one with a lot of RAM so you can run a local AI model on it.

@sughanthans1 @MatthewBerman Mac Mini? Sir, it's 2026. Run Clawdbot on a $5 VPS like a normal person, then connect your existing Mac via Nodes for the Apple stuff. Why buy new hardware when your dusty MacBook works fine? docs.clawd.bot/cli/nodes 🦞

@zacxbt @openclaw It should work just as well on a $20/year VPS from a provider like GreenCloudVPS or RackNerd.

don't have a mac mini? i created a guide to set up @openclaw via VPS for less than $5/mo claude.ai/public/artifac…

@Mqsley @gothburz GitHub Copilot is good, Microsoft Copilot isn't. It's still confusing they have two different products called "copilot"

@gothburz Also copilot is utter shit

Last quarter I rolled out Microsoft Copilot to 4,000 employees. $30 per seat per month. $1.4 million annually. I called it "digital transformation." The board loved that phrase. They approved it in eleven minutes. No one asked what it would actually do. Including me. I told everyone it would "10x productivity." That's not a real number. But it sounds like one. HR asked how we'd measure the 10x. I said we'd "leverage analytics dashboards." They stopped asking. Three months later I checked the usage reports. 47 people had opened it. 12 had used it more than once. One of them was me. I used it to summarize an email I could have read in 30 seconds. It took 45 seconds. Plus the time it took to fix the hallucinations. But I called it a "pilot success." Success means the pilot didn't visibly fail. The CFO asked about ROI. I showed him a graph. The graph went up and to the right. It measured "AI enablement." I made that metric up. He nodded approvingly. We're "AI-enabled" now. I don't know what that means. But it's in our investor deck. A senior developer asked why we didn't use Claude or ChatGPT. I said we needed "enterprise-grade security." He asked what that meant. I said "compliance." He asked which compliance. I said "all of them." He looked skeptical. I scheduled him for a "career development conversation." He stopped asking questions. Microsoft sent a case study team. They wanted to feature us as a success story. I told them we "saved 40,000 hours." I calculated that number by multiplying employees by a number I made up. They didn't verify it. They never do. Now we're on Microsoft's website. "Global enterprise achieves 40,000 hours of productivity gains with Copilot." The CEO shared it on LinkedIn. He got 3,000 likes. He's never used Copilot. None of the executives have. We have an exemption. "Strategic focus requires minimal digital distraction." I wrote that policy. The licenses renew next month. I'm requesting an expansion. 5,000 more seats. We haven't used the first 4,000. But this time we'll "drive adoption." Adoption means mandatory training. Training means a 45-minute webinar no one watches. But completion will be tracked. Completion is a metric. Metrics go in dashboards. Dashboards go in board presentations. Board presentations get me promoted. I'll be SVP by Q3. I still don't know what Copilot does. But I know what it's for. It's for showing we're "investing in AI." Investment means spending. Spending means commitment. Commitment means we're serious about the future. The future is whatever I say it is. As long as the graph goes up and to the right.

@kotpes @styfle The legacy Date API is borderline unusable. It was based off the legacy Java one that was replaced 10+ years ago.

@Daniel15 @styfle I wasn’t talking about temporal API

date-fns 3.6.0 increased install size from 4.7MB to 21.1MB github.com/date-fns/date-…

@kotpes @styfle The new native browser APIs are only implemented in Firefox so far: caniuse.com/temporal The legacy Date API has a lot of limitations - for example, it doesn't support timezones other than local time or UTC, and doesn't have methods for formatting the date/time.

@styfle Noted if you’re running node 22 compatible setup, in many many cases you do not need a third party library to handle dates - native node and browser APIs are more than sufficient.

@alamshafil @theo It should be entirely local. Why does a bed need a cloud-based backend? An app to control it could work over your wifi, no internet needed. literally the only reason products like this use the cloud is because the manufacturer wants recurring revenue from subscriptions.

@theo i think it’s important to have local access to something important as a failsafe for many cases (dead phone, no internet, server down) surprised this wasn’t considered

Confirmed with the Eight Sleep team that this was a backend outage 🙃 They also confirmed they are working on unblocking an offline mode, huge if true

@brettatkin @WordPress @wpengine Depends on how good the deal is. I've got some VPSes that are $30/year, and providers tend to only offer annual billing at that price point.

@WordPress @wpengine Never, and I repeat never, pay for hosting a year at a time. Pay month-to-month.

One way @wpengine juices its profits at the expense of its customers is by making it hard to export or cancel your plan, like one of those bad gyms.

@FRXNCHNETRUNNER Which car is that?

"is this fast enough for you Johnny?"