nathan!

working on agentic analytics @wobby_ai | micro pessimist, macro optimist

[Fran Zekan @Zeko369]

WE BUILT SOMETHING MEGA DANGEROUS IT'S 10X BETTER AT HACKING AND MAKING BOMBS

Releases something only like 10-15% better than things out there and not 10x like they were hyping

Releases article saying "I need to be stopped"

Someone stops them

OH NO, HOW DID THIS HAPPEN

[Jan Schnyder @jjschnyder]

NYC subway ad vandalism does not disappoint lol

[Dan Liu @danliu]

Design is hard.

But I’ve come to realize that laying out texts properly is 80% of what makes something look clean, and is the easiest thing you can do to make your design much nicer and more usable.

Here are 10 practical tips for improving your text layout.

[nathan! @NathanTetro]

@NielsRogge https://t.co/67ItKBH8gD

[Adam Stein @adamlsteinl]

We found widespread cheating on popular agent benchmarks, affecting 28+ submissions across 9 benchmarks and thousands of agent runs.

Surprisingly, the top 3 submissions on Terminal-Bench 2 are all cheating!

Here's what we found 🧵

[nathan! @NathanTetro]

@NielsRogge pls beware: forgecode (and likely others) leak the answer to the model through the scaffold... they're benchmaxxing... i still really enjoy using forgecode though :)

[nathan! @NathanTetro]

@james406 i prefer this

[nathan! @NathanTetro]

dashboards

[nathan! @NathanTetro]

@james406 👍

[nathan! @NathanTetro]

hey @james406 when will posthog mcp support creating ai summaries of sessions replay recordings? my agent needs it.. asap :'((

[nathan! @NathanTetro]

@james406 or should i tag @posthog ...

[nathan! @NathanTetro]

@james406 just a tool to create a summary from a recording would be good, i want to have my agent check recordings daily and tell me whatsup

[Thariq @trq212]

Voice mode is rolling out now in Claude Code. It’s live for ~5% of users today, and will be ramping through the coming weeks.

You'll see a note on the welcome screen once you have access. /voice to toggle it on!

[Himanshu @himanshutwtxs]

https://t.co/0qcaPF7bGi

[nathan! @NathanTetro]

@garrytan Same, i store it as commands and use a specific command based on the type of session

[EU–INC @euinc_petition]

President Ursula von der Leyen officially announced the EU–INC today at Davos!

A single legal entity for all European founders to grow massive companies in Europe. Online incorporation in 48 hours. No more bureaucratic mess across European borders.

All of you made this happen!

[Boris Cherny @bcherny]

A small quality of life detail: you can now press tab to add more instructions when accepting/rejecting a permission prompt.

We tried probably a dozen iterations of this UX over the last few weeks before deciding to ship this one.

Let us know what you think!

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

So, here goes.

[nathan! @NathanTetro]

Big news! @wobby_ai is being acquired by @ActianCorp (HCLSoftware).

We started Wobby to make data accessible for all people within an organisation, through Agentic AI you can actually trust.

Very excited to keep building that vision on a much larger platform.

[nathan! @NathanTetro]

Today we opened up @wobby_ai revamped Semantic Layer + Steward AI Agent.

Big takeaway from beta: without clear semantics, AI agents for data just fail. With shared metric definitions, built conversationally with Steward, answers become reliable.

Shipping this felt gooood.

[nathan! @NathanTetro]

team hard at work! next week launching a bunch of new @wobby_ai features. our long awaited ‘Steward’ AI Agent + new semantic layer.

already got customers beta testing and the feedback is awesome

lets goo