Reading up on ai-coding

Indiehacker A: > I vibecoded Mailchimp in just a few prompts > they raised prices so I built Slopchimp > you can use it too, for $49 / mo Indiehacker B: > I vibecoded Slopchimp > $49 is a price gouging scam > my slop is $5 lifetime

@yongfook

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

Day 5/ Composer predictions in the desktop app. Often leads to a double take with how on point they are. Included in the Pro plans without consuming usage.

@thsottiaux

Your ChatGPT subscription is now also a Devin subscription

@thsottiaux

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

We just let in every Pro and Max user from the Claude Code Projects waitlist! If you're new to Claude Code Projects, here's a 4 minute walkthrough to get you started:

@ClaudeDevs

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

Now in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of the most loved new features we've ever tested internally.

@OpenAIDevs

Most of what I do in Claude Code now are in Projects.

@shadcn

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

Bye bye Beehiiv 👋 I vibe-coded my own newsletter platform: 📧 Campaign management w/ editor 🖥️ Web archives (https://t.co/pypYdNhdlZ) 🔗 API support 🫧 List cleanup, deliverability reports It took a few prompts with Opus 5.5. I left Beehiiv because they raised prices for the 3rd time in 2 years. - My first yearly bill was $1,000. - My future bill would have been $4,000. Now I'm using AWS SES + MongoDB, and I will pay less than $300/year. Newsletter platforms charge per subscriber, when in fact the real cost is the number of emails sent. Subscribers will naturally become inactive, so you end up paying more for something that hurts your deliverability (sending to dormant subscribers = spam trap). So I've set a cleanup cron job for my newsletter alternative. It marks inactive subs as dormant, sends one last re-engaging email, and stops emailing them. Money saved. Deliverability increased. I also gain a priceless feature: Freedom. I can change the UI, add features, connect all my apps - anything is possible with just a prompt. I'm replacing Resend next. I love it, but it's very expensive ($400/mo)

@marclou

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

Day 2 of getting GitHub runners working on my Mac Mini 24/7 AI code factory

@DanielleMorrill

It was hilarious at first, funny at second but it’s starting to get tiring and borderline annoying, Grok Bot and Codex/Dots not stopping at throwing punches at one another

@GergelyOrosz

Day 3 (encore)/ We silently re-shipped codex cloud. It’s pretty good now

@thsottiaux

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 rolling out monthly Claude Platform API credits for Max and Team plans: Max 5x: $100 Max 20x: $200 Team: up to $500, pooled Works on any model, including Haiku 5.5, in your code or third-party harnesses. How it works and full terms: https://support.claude.com/en/articles/17154008-monthly-api-credits-for-max-and-team-plans

@ClaudeDevs

Reminder that I don't think you should run agents on a Mac unless you absolutely have to. It will slow you down massively and is not worth it.

@theo

While I agree, a minimal set of good skills can still make a difference. For example, a couple of skills I use on most tasks invite models to also think out of the box to propose alternatives (something they don’t usually do on their own), explore codebases for similar patterns to avoid redundancy (still a common issue), test changes as a real user and not with tests (also usually skipped by default) etc. This basically just skips all the back and forth I would do by asking all of this myself on most projects/tasks. So I would still invite everyone to experiment with having a minimal set of skills, but they should be reviewed and simplified/cleaned up with every major model release.

@linuz90

It took me 5 minutes to get into the Claude Startups program And you don't need VC funding anymore What you get: - A year of Claude Team - API credits - Priority rate limits - Deals on the tools a startup runs on How to apply: - Create a Claude Console account (the API one, not the app) - Use a company email, not Gmail - Go to

@adriamatz

Your side projects should be compounding very fast with AI. Every problem solved can be re-used or extracted into a generic module. Every design decision should make the next thing beautiful by default. Your agents should be constantly stealing from your past decisions.

@brian_lovin

You can basically work with agents to write markdown skills and put it on a cron job and do almost every useful type of knowledge work now

@garrytan

This guy is literally just running Claude Code on someone's GitHub repo and charging $1,500/mo If you have an audience on here you can monetize anything 😉 You can just copy his tweet to Claude Code and do it yourself for free by the way

@illyism

Just connected my ChatGPT Dot to iMessage using @thelinqapp. It's exactly like Instinct, except it actually has context on me + can use my computer + has my entire Gbrain knowledge graph and all my plugins. Instinct = feature not a product.

@awilkinson

I asked Opus 5.5 to make an interactive website companion for the latest @AcquiredFM Home Depot episode. It came out pretty nice! Water color illustrations all drawn by Claude, too: https://claude.ai/artifact/RdE6uE7WozcP2MLfx3BDky Episode here: https://www.acquired.fm/episodes/home-depot

@bcherny

I am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out. Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model: 1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing

@bcherny

I’ve tried rebuilding my website about 5 times since coding models came out. Design always was bad and nothing felt as simple as my old setup. Finally Codex built it, along with a small tool to add my writing and deploy the static site to S3. so enjoy https://karrisaarinen.com

@karrisaarinen

We're adding a new plugin to Claude Code: You should Know. It scans Claude's output for important information you might miss to help keep you in the loop. Enable it with: /plugin enable cc-plugin-you-should-know@builtin

@ClaudeDevs

We’ve been improving Loops a lot to automate work that should be automated In @slack or @linear just tell the agent you want to make a loop for something. The loop can auto pick models, connect to external services through MCP, can be triggered or scheduled. Some example loops from our team: * Investigate incoming bugs and propose fixes with browser tests * Find new Sentry errors and open fix PRs * Turn meeting action items into issues * Monitor engineering alerts and unusual cost spikes * Surface untracked container vulnerabilities * Scan and remove old feature flags * Watch feedback on workflows or product areas and keep an running document, slack or other sources

@karrisaarinen

Veeeery excited about mods, it’s basically middleware for Claude Code! You can create a TypeScript function that intercepts CC's internal events (tool calls, prompts, model requests and renders) and change what actually happens. You can also add your own UI and commands!

@lydiahallie

Get your Apple Reminders in Claude Code. RemCTL 2.1.0 now ships with a Claude Code plugin and mod, so you can always see what's left to do today, or in a specific list. There's even a sidebar! Get the update here: https://github.com/viticci/remctl @amorriscode

@viticci

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

@karpathy

all software is becoming malleable, so it was important for us to support this as a first class citizen in Claude Code, I hope more and more software becomes extensible like this! here are some of what I'm most excited about with mods:

@trq212

I built Apple Reminders…inside ChatGPT. This is real, and it's a native ChatGPT Extension you can try right now. Free and open source. Version 2.0 of my Reminders CLI, RemCTL, is out now with complete support for MCP and the brand new @OpenAIDevs MCP Extensions. With RemCTL 2.0, you have a power-user interface for Reminders inside ChatGPT for Mac. You can use keyboard shortcuts, there's a ⌘K palette, and view tasks as lists, Kanban, or Calendar. It's basically "Reminders Pro". But most importantly, you can work with ChatGPT in this Reminders UI and ask it to do whatever you want. Attach any task to a conversation, or select multiple ones and pass them to ChatGPT. I was inspired by @danshipper's concept of "Codex apps", and when I saw @mxstbr's announcement yesterday, I knew what to do. This feels like a brand new way of getting work done, and I'm excited to build more. Have fun!

@viticci

I literally can't think of a better risk/reward bet right now than building a ChatGPT plugin and getting in front of their 1.2 billion weekly users. As of yesterday, ChatGPT recommends plugins in the middle of conversations. Millions of questions get asked every day with no plugin to recommend. Each one is an empty slot. Facebook apps in 2007. iPhone apps in 2008. TikTok in 2019. Every big platform has a few months where distribution is free, and most people miss it. I saw this firsthand when I lived in SF building venture backed companies. They are sacred times! If I were starting this week: 1. Find a tool or workflow people already Google for or do by hand every week (PDF to Excel, invoice generator, weekly client reports) 2. Build it as a ChatGPT plugin 3. Write the description using the exact phrases people type into ChatGPT 4. Ship 5 of them and see which ones get picked up 5. Double down on the one with the most traction In 12 months these slots will be crowded but right now they're pretty empty. Most people will realize ChatGPT plugins were the biggest free distribution channel of 2026 sometime in 2027.

@gregisenberg

Same, but went with tinycast. Definitely interested in what Stephen's got going on here though. Raycast v2 has been really unfortunate and in the day of agentic programming, there's not a good excuse for drifting away from native.

@codejake

I gave Opus one night and one ask "Build my own Bot / Dot and it should use ChatGPT sign in and Claude subscriptions. Every agent get it's own VM" 12 hours later, TOT exists

@dhruvalgolakiya

You can finally close your laptop now and your agents will keep working. Codex cloud environments are here. Reusable environments mean less setup and faster starts, with your repo, dependencies, scripts, and settings already in place.

@OpenAIDevs

An early preview of experimental Bun + JSC with ahead-of-time compilation For Claude Code's CLI: 24% faster startup, 48% lower memory, 46% lower CPU, and nearly 2x larger binary size

@jarredsumner

Adapting for a world of software factories

@zachlloydtweets

Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo

@thsottiaux

it's basically impossible for someone to just "show you their prompt" now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, search the web for references, use other AI APIs, etc.

@trq212