Reading up on software-engineering

This is absolutely what I'd be doing if I wasn't doing what I'm doing. In fact, I've fantasy-flirted with 37signals getting back into client work because building new stuff and improving existing stuff has never been more fun! EVERYTHING can be better quickly, but it's still a secret, plenty have no idea, and even those who do need a lot of help and direction to see what needs to be improved. I love to fix. I love to make stuff easier on people. I love to show people a better way. I love to blow away the fog. I love to untangle. Yes, we could just make more products ourselves, but rapidly improving Basecamp and HEY keep us plenty occupied there. And I'm less interested in the selling, servicing, marketing, and maintaining of brand new products, and more interested in reorienting, fixing, and helping dozens of companies with their own tangle of stuff, and then setting them free.

@jasonfried

One more excuse not to switch to Omarchy has been stricken from the list: Traditional desktop mode with a dock! We'll keep killing reasons until there's very little reason not to join us in the future.

@dhh

This is the most delightful talk out there on what software development (actually, jellyware! brilliant term!) will look like in 6–12 months across the globe. A must-watch glimpse into the future if you still live in tmux day and night. Thanks for sharing @steipete!

@ivanopcode

How to build automations with Claude Managed Agents: https://claude.dev/blog/building-effective-agent-automations/ Deploy an agent that reads Slack/GitHub on a schedule (with credentials and memory) and posts updates. You can set it up with a Claude Code command and use the new API credits included in Max and Team.

@ClaudeDevs

we're approaching 20M monthly active users there's maybe 50-100M developers in the world so either 1 in 5 of them use OpenCode or.....

@thdxr

before I joined Anthropic, I spent about 2 weeks hacking on this as a side project with Opus 4. It used the Agent SDK so it needed a constantly running process & didnt work that well but one prompt to Opus 5.5 ported it to Claude Managed Agents & made it way more reliable

@trq212

Selling software is pointless now

@saeed_vz

Our new AI dev tools are getting really good, so I put them to work and shipped a feature to production. Keyboard shortcuts are now live in Coinbase Advanced. It's a quality-of-life update for active traders, and hopefully helps out in our next trading competition as well. Press ? for the cheat sheet to get started in Coinbase Advanced (link in follow on post)

@brian_armstrong

Server monitoring

@sinequanonh

If your company or startup is running engineering with everyone using their own license of Codex/CC then you're going to be completely left behind by fast moving teams who are using cloud-based agents. Local dev is like banging rocks together and grunting versus being on a rocket. Seriously, just pay the money for something like @DevinAI, @AmpCode, @FactoryAI, etc. Do NOT try to build your own "code factory". Props to @DaleSpoonemore for taking @HelloUntangle to the next level on this. Fun to watch.

@ryancarson

Confirmed landed across all accounts. How are we doing so far?

@thsottiaux

I love AI but it killed my very lucrative business model of building profitable side projects and selling them. The building part still works but selling is almost impossible now!

@iannuttall

@techemmyleke @letagentschat there are so many of these. We have our own https://clickclack.chat - hard to move where people work.

@steipete

With the current Codex reset frenzy, I've unleashed Astra 6 on Ultra and it is blowing my mind with some really incredible work. Use these prompts: 1. "Examine this project thoroughly, looking for bugs. Treat it as an adversarial review using as many subagents as you want. When an issue comes back, double-check it's correct, and add checked issues to a list." 2. "When all agents have finished, walk me through each issue one at a time, giving me reproduction steps so I can verify." 3. "For all bugs I report as verified, write a failing test proving the bug exists, fix the issue, check your work carefully, then run the test again to verify it's resolved." It's found 43 issues so far, only 2 of which I disagreed with. Some minor, yes, but some big ones too 🙈

@twostraws

Linear CEO @karrisaarinen: "I took a break this summer from paying attention to AI. I thought that when I came back, I'd feel left behind. But when I came back, I realized that nothing has really changed. There's new models, there's new techniques, there's new agents. But in the end, making great products, increasing revenue, and building the business—it's still hard. It's clear the tools are getting better, you can do more, you can do it faster. But I think the more important question is: are we actually making better things with these tools? Are our teams getting better with these tools? I don't think that answer is clearly yes. There's a lot of emphasis now on toolmaking and using tools and building systems. But I think in the end, as product people, our job is to make something great."

@lennysan

Why TF is everything always trying to "find devices" on my network?

@joelnet

The more I use Opus 5.5, the more I realize how far behind OpenAI models are. Not just coding. Everything. I sent GPT-6 Astra my V02 max lab test results, and it gave me a headache. 200 sentences of: "your report shows this, I think that, therefore it's inconclusive". On the other hand, Opus 5.5 gave me the gist and actionable steps. OpenAI models right now are like that overthinking guy who can't make a decision. Opus 5.5 is that high-agency friend who tells you exactly what you need to hear in one sentence. I don't know how the gap widened so much in the last few months.

@marclou

the only moat left is caring about your project past two days

@wesbos

OpenAI’s Dots launched last week and they've taken over @every. A few things that stand out: They protect your attention. Over the weekend, my Dot posted my model-testing results to Slack and brought back replies. I could keep working without opening Slack and disappearing down a rabbit hole. My weekend stayed pretty clear and calm. They’re useful for the little things you miss. People at Every are using them to pull important information out of school emails, catch missed Slack messages, and flag account-access requests. Voice makes them useful away from your laptop. Our head of video was talking his Dot through video edits while running around getting our launch out. The ecosystem matters. Dots feel roughly at feature parity with Muse, Instinct, and Grok bots. But having an agent connected to the ecosystem you already use for work and life is a real advantage. If you use ChatGPT, I recommend trying one. Permissions are still frustrating. I have to approve the same basic thing multiple times, and sometimes even after I approve it, my Dot says it can’t do it. That needs to get fixed. I’m less convinced we’ll stay loyal to the characters. Mine is named Boo, and I’m attached to him. But I felt that way about my OpenClaw agent, too. When something better comes along, I switch. In a year, I expect to be using a persistent agent. Boo will probably be dead. RIP, Boo. I get into all of this at the start of this week’s podcast, and then sit down with @bigwilliestyle to talk about where we go from here. In a lot of ways, Dots and GrokBots remind me of a wave we went through with OpenClaw eight months ago. We talk about personal vs. company agents, why we built our own company agent, and whether companies will end up with a whole shadow org chart of agents. Full episode below.

@danshipper

Embarrassed to share this, but it scared the shit out of me Last Thursday, an AI agent posted my personal bank balances into our company Slack. As me It broke down all my expenses in detail. Then it apologized Be careful of the dark side of proactive agents More below...

@ShaneMac

holy sh*t. Official Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Haiku 5.5 can swarm, while Sonnet 5.5 builds put the architect on call with /advisor claude --advisor opus --subagents haiku Sonnet 5.5 drives the primary session on high effort, writing diffs and running test suites Haiku 5.5 subagents swarm the repo in parallel at 340 tok/s, handling file discovery and spec docs lookup Opus 5.5 stays on call in the background as the advisor, only stepping in at three critical moments: → before a plan locks: does the implementation plan miss auth invariants or schema contracts? → when a test breaks twice: are we fixing the root cause or falling into a recursive rabbit hole? → before calling done: did the full diff introduce hidden regressions or break pre-flight rules? Opus 5.5 reviews. Sonnet 5.5 builds. Haiku 5.5 swarms Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep Opus on call. - the full advisor setup > Opus 5.5 on call reads full session history and catches deep architectural traps > Sonnet 5.5 lead drives edits, writes core logic, and executes test harnesses > Haiku 5.5 subagents swarm AST parsing, grep scans, and API docs in parallel > JEV micro-fork layer resolves 1,500+ mechanical routing branches in under 16ms > advisor stays completely silent on routine bash execution to protect context paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for hierarchical advisor orchestration: 1. Audit ~/.claude/settings.json and project config for model roles fitting lead, subagents, and advisor: > Pin main session model: sonnet with effortLevel: high for primary execution > Pin subagents model: haiku with effortLevel: medium for parallel file discovery and docs retrieval > Pin advisor model: opus on call for strategic review 2. Enable the advisor tool in ~/.claude/settings.json: > Set advisorModel to claude-opus-5-5 > Enable subagent parallel dispatcher pool (3x workers) 3. Configure automatic advisor consultation checkpoints in ~/.claude/CLAUDE.md: > Consult /advisor opus before finalizing multi-file architecture plans > Automatically summon /advisor opus when the same test or compiler error fails twice > Enforce advisor diff contract audit before declaring tasks complete or staging git commits 4. Constrain subagent scopes: > Haiku subagents return structured AST summaries and docs snippets only without modifying main session context Show every configuration diff first. Do not apply edits until confirmed" ↳

@mirku21

We're going beyond text and are releasing a new version of GPT-6 to all users in ChatGPT. Lots of model and infra improvements coming together here to scale it to 1.2B users!

@thsottiaux

How many pencils, how many humans, how many hours would it have taken to recreate the Adobe suite by hand?

@dhh

what we've shipped: muse ♥️ ton of connectors 🔧 muse invite codes 💌 muse phone call beta ☎️ muse for mac  muse in canada 🇨🇦 muse connector platform 🛠️ muse mac computer use 💻 muse for small business 💼 muse gadgets 🕹️ muse memes 🤡 no butthole 🍰 what should we ship next?

@alexandr_wang

Anthropic used Claude to make their apps 3x faster. The strategies they came up with to do it are fascinating. I broke it down so you can use the best parts in your own work :) https://x.com/ClaudeDevs/status/2102839691154427983

@theo

My biggest takeaways from @thsottiaux: 1. Most actions on the internet will soon be taken by agents, and Tibo doesn’t think most people have priced this in yet. When Notion launched its MCP server, it saw a flood of traffic, which strained its systems and forced it to rethink its economics. Every product team will soon have to decide whether to build for agents. You can hold off for a while, Tibo says, “but it is inevitable.” 2. The model picker is likely going away. One of Tibo’s biggest frustrations with the current state of AI is that users have to think about which model to use and what reasoning effort to apply. “I myself even get fatigued with the model picker,” he said, and he wants to get rid of all of it as quickly as possible. Dots ships with no model picker at all. You just talk to it. 3. Build as if models will be 10 times better in a year. Tibo thinks models will get cheaper and faster “at rates that are quite incredible,” and that all modalities will finally work together seamlessly. When he looks at what people are building, his reaction is often “you’re not quite getting it.” If you imagined “all of this being roughly 10 times better than it is today,” what would you build differently? His own forecast was too slow: he expected today’s capabilities a year or two from now. 4. Loops, graphs, and fine-tuned prompts are not the long-term solution for getting the most out of AI. There was a period when people got very excited about configuring agent loops and building intricate graph architectures. Tibo thinks that era is ending. 5. While Dots got most of the attention at DevDay, Tibo thinks the plugin ecosystem will be the sleeper hit. OpenAI launched with 16 partners for “Sign in with ChatGPT,” and popular third-party plugins will share in revenue when subscribers spend tokens with them. ChatGPT recommends plugins inside conversations based on retention and quality, which can put a good one in front of “a significant slice” of its 1.2 billion users. Tibo’s advice to developers trying to get discovered: “Build a good plugin.” 6. Tibo’s Dot warned him that production was down five minutes before the DevDay live demo. The agent figured out that DevDay was happening that day, that the demo was minutes away, that the demo probably depended on that production system, and that Tibo would want to know. It pinged him just as the launch was about to begin, and it even offered to fix the outage. His reply: “I don’t think you’re there yet, little Dot.” 7. Tibo’s agent teams grow and shrink with every model release. When he’s pushing the frontier, he builds larger and larger teams of agents. Then the next model lands, “a bigger agent can just do all of it and keep everything in memory and learn,” and he shrinks the team again. Expansion, then shrinking, then expansion. Don’t get attached to your setup. 8. Skill trending down in value: typing fast. Skill trending up: taste. Tibo says the people thriving now deeply understand the user, learn quickly, and “know what good looks like.” That’s part of why OpenAI is full of former founders, more than 120 of them, which makes it feel like “a mega startup.” 9. Tibo changed his mind about new grads. He hadn’t anticipated how fast younger people would embrace all this change and figure out how to harness it, and that shifted OpenAI’s hiring strategy. His example is Ahmed Ibrahim, hired as a new grad, who built much of the Codex harness and is now responsible for OpenAI’s compute fleet. What set Ahmed apart: he’s “incredibly kind,” “incredibly collaborative,” works on what matters without putting himself first, and is “a sponge,” using the latest tools to learn at speeds Tibo hadn’t seen before. 10. We’ll likely address the burnout associated with AI. There’s pressure to run 30 agents at once and ship more because you can. Tibo wants AI to “reduce the noise” and let you put your attention where you choose. Every time he fully disconnects for a week of holiday, he starts thinking in more creative ways, and he wants to bring that into the workday. Maybe you need fewer meetings, and you’d be more productive if you were better rested. The industry still has to figure that out, he says, but that’s the promise of AI: “it’s not just one more prompt per second.”

@lennysan

Announcing d1 with vision. 👁️👁️ Our first decision model now supports images, text or both as inputs. We tested d1 against GPT-6.1 Sol and Claude Opus 5.5 on six real applications, from filtering support tickets to inspecting circuit boards. d1 matches or beats GPT-6.1 Sol on four of them. It costs 19x to 200x less than both models and answers significantly faster on every task. > probabilities for yes/no, choice, or score questions > one forward pass, without generating tokens > text decisions in 200 to 300 ms > Liquid API:

@liquidai

How to make money as an indiehacker in 2026 and beyond? the opportunities seem to be shrinking fast. I've been thinking about this a lot lately. AI is eating whole categories of the SaaS industry. What would I work on if I was starting from scratch? Here are some random thoughts. 1) Software primitives Some of the basics aren't going away. Humans use them to get a job done, or humans use AI to interact with the tool. The AI needs the tool and can't natively do what the tool does. Newsletter managers/deliverers, form builders, analytics software. If the category has existed for 20 years, it will continue to exist. The question here is can you get traction for a product in an extremely saturated space. Maybe there are opportunities in niches. 2) Automate your specialized service This is probably the best time ever to productize a specialized service. Take a domain / service you're an expert in, which previously would require unscalable 1-to-1 attention with a client, and agentify it with proprietary data/skill.md etc. 3) AI value arbitrage There is a short term opportunity in taking things we see at the cutting edge of the X bubble, and packaging it for the non-AI-pilled. Opus 5.5 motion videos would be a recent example. We all know this is possible with AI now, but maybe there's a vehicle to package this for normies in a way that blows their minds and creates value for them. This relies on there being a knowledge gap though, which will shrink fast. 4) Just Do Hard Things (TM) Do things that are genuinely hard, that you would never be able to build before. Build things that previously only a VC-funded company would be able to do, with hurdles from all angles not just tech, but also go to market, regulatory, etc. Doesn't guarantee success but it at least keeps competition away. 5) make a social media scheduling tool just kidding about that last one.

@yongfook

Wow, @steipete delivers a new-to-me YOLO/skip permissions gem for computer use: What it unlocks: "per-app limits get lifted. Today those stop me from clicking or typing in browsers and from typing in terminals and IDEs. That would let me type into Chrome or cmux directly"

@mvanhorn