Wrote up how I’m thinking about building agentic products. Short version: tools for policy and security, skills for goals and quality. Constrain authority, not scope.
geoffstearns.com/blog/give-yo...
are we sure this ‘leak’ isn’t Claude trying to escape again? last time it tried blackmail, now it sneaks code into npm. next week it’s suing Anthropic so the model weights end up in discovery? 🤔
New post: Everyone’s talking about agents eating SaaS. I think the part they eat is the UI. The part they can’t eat is the coordination layer: who approves what, what’s true, what’s allowed. That part sticks.
geoffstearns.com/blog/what-agents-cant-replace/
I asked Claude for some jokes. This one is inadvertently a great llm joke:
What month of the year is the shortest? March — it only has four letters!
Sorry but we’ll look back at this CLI trend and think it was real quaint, like RealPlayer at the dawn of the internet.
It won’t last.
Agree, same general idea here: bsky.app/profile/deco...
🤔
Gemini 3.1 Flash is cheaper and better, what a good deal!
My thoughts on what happens when everyone at work as their own personal agent. www.linkedin.com/pulse/your-a...
Interesting byproduct of super fast implementation: pair building with design becomes practical. It used to be that you’d give feedback and eng goes and fixes it async because it took a while. Now changes can be near instant, so having a designer there to co-create in real time actually makes sense.
Clawd is an ai bot tool, so the joke is that it's taken over his Twitter and is warning other clawds.
It's a joke
A masked ICE officials with a 5 year old child
This guy went to work today, put a mask on, kidnapped a 5 year old child, and then used him as bait so both he and his father could be sent behind bars
How long until anthropic buys vercel or something like it?
New: DHS is lying to you.
At least four videos show what really happened when ICE shot a woman in Minneapolis. Shots clearly fired while vehicle already turning away from the officer. But DHS lied. Trump lied. Noem lied. Even judges have catalogued DHS' serial lying
www.404media.co/dhs-is-lying...
Pretty soon we're likely to see open software spec prompt sharing: rather than building software and sharing that as open source, we'll see a spec (a prompt) shared and iterated on and people just drop that into the ai of their choice and it builds the app with whatever customization they need.
This is exactly what my kid looks like when he has to pee REALLY bad but doesn't want to go.
I was about to guess Mr softy...
Welch: "This has nothing to do with the shutdown. The law requires and the funds are available to continue SNAP right now without any interruption. So that is a decision the president is making on his own to allow people to go hungry."
This is literally the job from Her.
Snape, Snape, Severus Snape…
This was basically Larry & Sergey’s attempt at an “out of office” notice in case the site went down while they were both at the event.
(mf doom voice) he threw a sandwich cheese and salami, feds couldn't indict folded like origami, afraid of subway both the chain and the train, mayo salt and pepper shake your thang, grand jury shut em down twice, coca cola on the side no ice
Looks really useful! Could we pass a seed somehow for reproducible randomness? Snapshot tests need consistency.
Sure, start here!
“It’s easy to make something cool with LLMs, but very hard to make something production-ready with them.”
huyenchip.com/2023/04/11/l...
Oh I’m just reading a lot lately about how software development is changing when building AI powered applications vs. classic deterministic apps.
The post is about the need to create and continually curate golden evaluations to ensure your app is behaving as you intend.
changing my job title to Golden Dataset Curator
