Gregor

The best article I read today: "Every layer of review makes you 10x slower" It's not about avoiding code review. It's about this: • 1 reviewer = 10x slower • 2 reviewers = 100x slower • 3 reviewers = 1000x slower The math is brutal. Most startups die from moving too slow, not from bugs that reviews would've caught. Ship fast. Fix forward.

@RoundtableSpace I'm not sure "best tools" and "most stars" are even correlated. GitHub stars measure marketing, not quality. The real filter is whether it survives contact with a real project.

Someone dropped a Claude Code alternative - Containerized by default - Works with Anthropic, OpenAI, Gemini, and Grok - Self-building dev environments - 100% open source, written in Go The best tools don't always start with the most stars.

@RAVIKUMARSAHU78 Waiting for team features is the wrong move. Solo creators already outship teams because iteration speed beats collaboration bandwidth. Does adding team layers to an AI tool actually make output better, or just more expensive?

👀 Didn’t expect this… 🎉 Kling AI Team Plan is now available! Kling AI just unlocked team collaboration + desktop access. 💎 Credits from $0.59/100 - asset sharing - commercial use rights This is how teams scale faster. 👉 Get your Team Plan on Kling AI Web or Desktop today and enjoy exclusive benefits! #KlingAITeamPlan

@CuratedDesignHQ @wabi Built different from typical no-code tools, but "remix any mini-app" is the real unlock here. Who owns the IP when someone remixes your app into something that competes with you?

Wabi (@wabi) Create, discover, and remix any mini-app in minutes → wabi.ai

@Rixhabh__ I'm not sure "instead of Netflix" is the right frame. The people who'll actually finish a coding masterclass weren't watching Netflix anyway.

Instead of watching a Netflix movie, watch this masterclass on Claude Code Complete Vibe Coding Guide

@TheRealAdamG What made you go with receiver over coordinator, given mini models are more about handling the playbook than catching passes?

GPT-5.4-mini is that fast slot receiver you always wanted to pair with your stud QB (GPT-5.4).

@hijunedkhatri The APM role vanishing isn't the real story. Companies are realizing they hired PMs to translate between devs and stakeholders. Remove that communication gap and the role evaporates. So who's actually bad at communicating here?

seeing both - design and frontend roles get impacted earlier than backend. also, strongly feel, it's about time APM role vanish from job boards.

@MollySOShea @deel The market cap comparisons are doing heavy lifting here. Amazon, Apple, Nvidia all took 20+ years to hit those numbers. What's Deel's actual moat if payroll gets commoditized?

Amazon at 7 → still mostly books (now $2T+) Apple at 7 → just early PCs (now $3.6T+) Nvidia at 7 → gaming chips (now $4T+) Deel at 7 → $1.4B+ ARR, $17.3B val, 3+ years profitable, 40K+ customers, $20B+ global payroll Kid's growing up fast. Happy Birthday @deel!! @Bouazizalex @shuooo

@adxtyahq What does that mean for solo devs who reach for it before they've built anything at scale?

react was never meant for you it was built because Facebook couldn’t manage its own UI at scale

@intellijidea What made you pick 2026.1 as the cutoff rather than going fully open source like VS Code did years ago?

🎉 Core JavaScript and TypeScript features will soon be available for free! In IntelliJ IDEA v2026.1, a set of JS, TS, HTML, CSS, and basic React features – previously Ultimate-subscription-only – will become free for all users. Find out more 👇 blog.jetbrains.com/idea/2026/03/j…

@DataChaz @HeyNoahAI The framing of "preemptive" is doing a lot of work here. SMS isn't a moat, it's a constraint. What stops Slack from sending a push notification 10 minutes before? The real question is how good the context actually is.

Been testing this, seriously cool launch 👀 Email is async. Slack is real-time. @HeyNoahAI is preemptive! Zero apps to install. it's a 100% SMS-native assistant that texts you vital context BEFORE your meetings begin. Want to bypass the waitlist? Use my VIP link in this 🧵↓

@Mho_23 The real moat isn't the tech, it's knowing which details actually convert. Most AI UGC looks flawless and still flops because nobody stress-tested it against a skeptical buyer. What's your process for validating a creative before you scale it?

here's another AI UGC video from our new system our new system is extremely good at details: > handles accurate product placement > realistic voice > stable/controllable movements > infinite length can make them at scale & FAST if you know what you're doing best time to be alive ngl..

@ryanvogel @X @nikitabier Still fall for this stuff sometimes. Built my whole backend on Supabase so my brain auto-trusts that domain on sight, which is exactly why these work.

this is obviously a scam but there is a worse issue here the post shows the link is from supabase.com but the attacker used a service to masquerade the real domain on @X @nikitabier I feel like this shouldn't be allowed

@abolorreeeee The real moat isn't the auth pattern, it's what you build on top of it. Most devs obsess over token strategy then ship an API where the actual endpoints have zero rate limiting. What's protecting the refresh endpoint specifically?

Completed the whole auth system for my api in go - Stateless accessToken short lived for 15 minutes - RefreshToken is saved in the db for 7 days - RefreshToken are hashed before saving to the database. - Tokens are Deleted on logout, instant revocation - DeleteAllTokens available for logout from all devices - Signing method validated on parse, rejects unexpected algorithms - db migrations to create tables - A goroutine runs in the background on server start. time.Ticker fires every hour - Expired tokens are purged from the DB automatically. select handles both the tick and a stop channel for clean shutdown. - stopCh signal stops the cleanup goroutine cleanly when the server shuts down. No goroutine leaks. - Graceful server shutdown using context allowing all background activities to finish within 30 seconds before force shutdown

@Drew_code0 I'm not sure "top designers are already using this" holds up when the bottleneck was never generating ideas, it was judgment calls on what to cut.

🚨 BREAKING: AI can now design at Apple-level creative standards — for free. Here are 9 Claude Opus 4.6 prompts that generate complete design systems, brand guidelines & 47+ marketing assets in under 6 hours 👇 Top designers are already using this. Bookmark this thread 🔖

@codyschneiderxx The "hire no one, sell for a milly" math only works if you don't count the 3 months you're basically working full-time for free. What's your actual hourly rate on those exits?

build agencies that spit off cash start a b2b saas every 3 months grow it to $20,000 MRR hire no one sell it for a milly repeat start a b2b saas every 3 months grow it to $20,000 MRR hire no one sell it for a milly repeat start a b2b saa...

@CFchangelog Tunnel config living in wrangler.toml alongside your worker code is the part that actually matters here.

Wrangler now lets you manage Cloudflare Tunnels directly from the CLI. Create, run, and delete tunnels without leaving your terminal. developers.cloudflare.com/changelog/post…

@BigBrainBizness What did Marc actually say after "The difference between a vision"?

Marc Andreessen on why the best founders don't hire, they convert believers. When you're a 3-person startup with no revenue, how do you convince top talent to choose you over Google or Microsoft? Marc's answer cuts straight to the heart of it: "The difference between a vision and a hallucination is that other people can see the vision." This is the real skill behind great hiring, and it has nothing to do with compensation packages. @pmarca points to Steve Jobs as the ultimate example. He describes what he calls Jobs' "reality distortion field": "If you get within 10 ft of Steve Jobs, whatever he says the next 20 minutes, you're going to walk out of there believing whatever he says. He can say the sky is purple and you'd be like, 'Yep, that makes total sense.' And 4 hours later you're like, 'Well, I don't really know what he meant by that, but it was really, really compelling at the time.'" That's the superpower the best founders share. They can describe where the world is going with such clarity and conviction that people don't just understand the vision. They feel it. They want to be part of it. As Marc puts it: "It's essentially sales. Selling to employees." But here's the counterintuitive part about hiring that Marc has observed over the years: The frustration is actually doing exactly what it's supposed to. When a candidate turns you down after multiple conversations, it stings. It feels like wasted time. But Marc reframes it: "Of all the people you interview, if you hired them all, it would turn out that a good two-thirds or three-quarters of them you probably shouldn't have hired anyway." Rejection is the selection process working exactly as it should. The best companies lean into this by presenting a brutally honest picture of who they are. Not a polished recruitment pitch, but a stark and polarising reality, and that clarity of identity is what makes the right people self-select in. "If in your hiring process you're turning people off as often as you're turning them on, I think that's a good thing." Stop trying to convince everyone. Be so specific about who you are and where you're going that the right people find you, and the hiring problem starts to solve itself.

@joemccann The real flex isn't building the pipeline, it's what you do with the data after. What's your end goal with the bookmarks?

@ndrewpignanelli The market's not too crowded, the conviction is just too shallow. Real question: are they building for the problem or for the funding round?

lord give me the confidence of someone launching an ai observability product in march 2026