Swyx gave me the “closing keynote” of AIE code, aka everyone is tired or flying out
so if you’re not one of those please come to mine tomorrow at 5pm
it’s called “the sweet side of the bitter lesson”
Show more
we need fewer one shot demos and more tools that show how you can collaborate with models to bring your vision to life
A few folks asked to see how I use the AI Assisted Tween & Paint harnesses, so I put together a little video with Claude!
Linking below the workbook :)
too many people building agents and not enough people using software to improve the quality of fish
we have a winner for the most absurd AI startup ever
this Peter Thiel backed company uses AI robots to stab fish in the brain so they taste better and last up to 3x longer
it's called Shinkei and it modernizes a centuries-old Japanese technique
dozens of Michelin-star restaurants are already lining up to buy the fish
here's how it works:
> the problem is when a fish gets caught, it usually just suffocates on the boat
> that stress floods the meat with hormones and lactic acid, which hurts the flavor and texture
> the old Japanese fix for this was spiking the fish through the brain right after the catch, which stops all that
> but doing it by hand is impractical for most American fishing crews
> so Shinkei built a fridge-sized robot that sits right on the boat's deck
> the crew feeds in a fish and AI identifies the exact species, so it knows exactly where the brain and gills are
> the robot then drives the spike through the brain and cuts near the gills in about 7 seconds
> the fish goes into an ice slurry so the blood drains out
> so the fish doesn't sit there stressing out, and that tasty flavor and texture is preserved
example number 5,392,417 of how AI can be applied to literally anything
Show more
a pattern I’m liking: creator apps like Instagram Edits and Roblox Studio shipping with built-in MCPs, so agents can do some of the work while power users can collaborate and continue the work in tools that they're used to
Show more
feels like it's really coming together
@rayansadri This is generally why SF tech is so far ahead: people move a lot and everybody learns from each other, so every SF eng/pm/etc is the aggregate of many life experiences.
This was less strange in an era where nobody cared about secrets.
Show more
The third SOTA wife has entered the chat, and this one is fresh off his exit at Anthropic.
Sarah (Head of DevX at Cerebras, @MilksandMatcha) and Vivian (GP at Y Combinator, @vivianmshen) sit down with @trq212 right after his last day at Anthropic.
What was supposed to be a quiet start to his funemployment era turned into getting outed on Twitter, CEOs in his DMs, and a next-day debrief on the pod.
01:16 Meet the third member: leaving Anthropic
03:15 YC's COVID batch
05:17 Over-raising and shutting down Multiverse
08:58 Toronto, Bay Area high schools and raising kids
12:39 First impressions of SF and tech Twitter
18:32 Going viral with Claude Code content
20:26 Why Anthropic, and idolizing the labs
22:33 Can startups survive the labs?
29:53 Labs as Hogwarts houses, and friendly rivals
35:21 Honeypots, spies and the apocalypse
Show more
one of my favorite prompts for agents like Instinct is location based reminders
e.g. "Keep track of when I've done my laundry. If it's been more than 5 days, remind me 30 minutes after I get home on a week day and bug me until I confirm or delay"
Show more
this is basically the bitter lesson at work
the smartest models will need fewer and fewer tokens, they won't need to verify their work or check it for bugs, they will just be right
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether
i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis
Show more
one week in my takeaway is that you don't need unlimited tokens to do great work, the $200 plans are amazing
and this is the most expensive intelligence will ever be
Okay I read it.
Will and Joe present an investment thesis for a proposed inevitable future world.
I deeply hope the world they propose as a given never happens. The world is a dystopia where intelligence is abundant while ordinary people see no stable, optimistic future for themselves or their children.
I do not want my kids or your kids to live in that world. Let's make a different world.
Show more
the solution to economic doomerism is to be even more AGI-pilled
I believe in a well-aligned ASI that can explain its work and bring us along, one that makes each individual maximally effective
There’s 100% a kind of mania you can get into with coding agents, where it feels like you’re getting a lot done and working all the time but nothing is really happening.
I think it's often a form of avoidance of something else in life.
Show more
I think the same is true of creative fields, like I see artists really worrying about AI
but I wish so badly that I could sketch animation ideas and character concepts for my agent to flesh out instead of trying to find examples
I don't have the language!
Show more
very weird thing happening rn
technical people are sad, they think their skills are now useless
non-technical people are desperately wishing they were more technical so they could use agents better
very weird thing happening rn
technical people are sad, they think their skills are now useless
non-technical people are desperately wishing they were more technical so they could use agents better
courage in shorter supply than genius
The coding interview is dead, at least for my team at Anthropic. I've seen enough to know that it no longer provides signal. I removed it from loops this month.
I have a spicy, optimistic take - I think there's an opportunity for junior engineers:
Show more
feels like there needs to be a new way to distribute opensource software such that people can modify via agents but also get upstream automatically merged in
coding agents can do this but they won’t do it automatically
Show more
experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused
my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them
Show more
experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused
my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them
Show more
going to be sharing my WoW forever shaman build at the AIE Code closing keynote
