get filthy rich & listen to dirty tech. less time working means more time raving. project manager at i can’t say. dropping tracks & productivity methods
ai has one annoying habit.
it really wants to agree with you.
so try this:
/redteam
put it at the start of your prompt and ask ai to critique your idea aggressively.
instead of telling you why your idea is brilliant, it looks for:
→ weak assumptions
→ gaps in your logic
→ things you haven't considered
→ reasons the idea could fail
basically, stop asking AI to be your biggest fan.
ask it to be the person trying to tear your idea apart.
you'll usually get a much better answer
@kimmonismus if all these models are coming this fast, are we heading toward an ai arms race where the releases matter less than what people actually build with them?
GPT-6 Astra vs. Claude Fable 5.1 vs. Claude Fable 5: Reactions on Cost, Coding & Benchmarks
Hear @petergostev’s initial take on GPT-6 Astra by @OpenAI vs Fable 5.1 by @AnthropicAI directly. https://t.co/HU5RPUajc7
got annoyed re-typing the same commit message structure every day. automated it.
built a tiny git hook that runs a saved prompt against my staged diff and drafts the commit message, i just edit instead of writing from scratch.
action: add a prepare-commit-msg hook in .git/hooks, have it call your model of choice with the diff as input, output feeds straight into the commit message field.
pro: turns "write a commit message" into "fix two words," most days.
con: it'll happily write a confident, wrong summary if your diff is messy, always read before committing.
not a big automation. just one less blank text box every day.
GOOGLE 🔥: Lyria 3.5 has been released and is now available on Google AI Studio, Gemini app and APIs.
> "Our advanced, full-song generative model with enhanced audio fidelity and vocal clarity, optimized for precise prompt adherence and rich, cohesive musical arrangements."
@HackItMax i'm with you on that one. being the person who isn’t always first can feel like a weakness early on. eventually, you realise it can become one of your biggest strengths
Many startup employees do not recognize the sheer litany of ways that a founder can screw you over without you even knowing. Founder trust is one of the most important things to look at when you’re joining a startup.
From cutting you out of M&A, screwing your retention pool, overdiluting your equity, firing you before your cliff, not having attractive options exercise plans, poor 409a price management, not telling you about QSBS / early exercise, blocking you from participating in secondary, obscuring company performance and many more.
Many many decisions that are made in rooms you are not in as an employee where the only thing that matters is: “does the founder have your back?” Great startups with untrustworthy founders lead to poor outcomes and often good startups with trustworthy founders lead to great outcomes.
Pick wisely.
@AndrewCurran_ ai safety is becoming a geopolitical issue, not just a tech industry one. when the U.S. and China start discussing guardrails together, you know this is moving into a very different phase