banned my Claude form EVER telling me "go to settings and..." π
if it can do the step itself, it does the step. the only things it hands back are the bits that are physically mine, like a login or a 2FA code
a year ago shoppers coming from AI were 9% LESS likely to buy on US retail sites. now they convert 90% better π€―
and Adobe expects AI traffic to nearly double on Black Friday. AI is either talking about your brand or ignoring it, and this is the worst quarter to be ignored...
check out the Brainlabs AI visibility page
saas runs on software, so everyone is building a software factory
the hardest part of building agents is the context (or knowledge that they have)
if youre building agents, you should be building a knowledge factory
you an spot AI-made designs in about 2 seconds... em dashed, those double slashes, an arrow on every button and that BLACK background π
Liz, our CMO, shows how she gets Claude to build something that actually looks designed, and it starts before she even writes anything.
@DarceX26 good shout. and thatβs the bit that matters... double the rate plus 2-3x the thinking is how you end up at 4x the bill π worth checking your effort settings before switching
Fable 5.2 vs Opus 5.5... The New Stack ran both and got the same scores, w Fable costing almost 4x as much π€
even Anthropic says start on Opus. Save Fable for those massive builds
if youβre using it for real work, whatβs the one job where itβs actually been worth the extra?
Google, OpenAI & Anthropic are at the stage where, unless you frequently switch between them or actively test them, you are probably very happy with the series of releases in the past two months. Even the model releases that are not as strong represent large capability gains
this is so underrated...saying "i don't know this yet" out loud is what lets everyone else start asking questions.
an honest leader beats one who's faking it every time
The best thing a leader can do rn is admitting what they donβt know.
Just had a training w a @cxodev client and the senior leader that brought us in was transparent abt their AI use: βIβm not doing any of this stuff. But I want to.β
Gave everyone permission to ask & learn.
A new faux pas Iβm seeing: dismissing a teammateβs well-structured, probably decent agentic output as βAI slopβ because you donβt want to read it.
If a teammate (or agent) has skillfully prompted and carefully edited something to solve a problem or communicate with the business, it isnβt automatic slop just because AI generated it. Thereβs often good stuff in there... if itβs long or you're multi-tasking, feed it to your agent.
Donβt overuse the term "AI slop" for any AI output. Save it for the actual sloppity slop, ya know?
another reason we love @NotionHQ ... it's not tied to ONE LLM
the model's the bit you can swap. your context & your JUDGEMENT are the bits you can't
full episode in the comments