AshkOff

Freelance ninja

[Naomi Saphra @nsaphra]

I am begging people who write like LLMs to read Style: Clarity and Grace. Or this 4-pager on character/action grammar. It's not about "genuinely" or "honestly". The tics flag obfuscatory, out-of-order sentences. It's hard to evaluate if they mean anything. https://t.co/zzPJkcsi0R

[Ed Leon Klinger @edleonklinger]

I've been tinkering with an AI to increase my “luck surface area” (basically, to find interesting opportunities that exist across my entire network) and the results are ... pretty interesting.

Built on my corpus of personal & professional data - everyone I’ve met with, emailed, talked to, thousands of call notes, LinkedIn connections, emails, Slacks etc. Plus it does its own desk research on my contacts overnight (did that by itself without being asked, weirdly).

Example - it suggested I introduce Marco (an insurtech founder, hiring for multiple roles) to Ben (an insurance headhunter I really rate). It pieced that together through a combo of Granola transcripts, emails, LinkedIn messages, and internal Slack messages.

Powered by a social graph algorithm that scores relationships and potential intros - based on things like relationship strength, recency, communication style, and “likely-mutual-value”, etc.

I left it running overnight, and it:
> found people who have helped me with intros & advice, but where that help hasn't been reciprocated by me - then it suggested actions I could take to repay the favours
> remembered that a colleague described her ideal mentor to me in a meeting *a year ago* - found someone in my network with the exact right experience, and drafted an intro
> surfaced a bunch of insights about my own life - like a drop-off in social & fitness activity since becoming a dad(!) - and set up a local run club on WhatsApp

The suggestions are… surprisingly good! And devoid of the usual AI slop.

I talk a lot about luck surface area - putting yourself in situations where good things tend to magically happen. This is the first time I’ve built something that actually tries to increase that surface area for me and my network.

I’m quite encouraged by the results, and it was surprisingly easy to build (with @claudeai, of course). Happy to share how for anyone who is interested in building their own.

@bcherny

[Justin Skycak @justinskycak]

"Your lack of urgency is wasting your potential."

[Lenny Rachitsky @lennysan]

It really is

Grab it here: https://t.co/3UumwpTsp9

[Mintlify @mintlify]

we're hiring across sf & ny
┏━━━━━━━━━━━┓
┃ Applied AI Engineer ┃
┃ Product Engineer ┃
┃ Forward Deployed Eng ┃
┃ AE, SDR, CSM ┃
┗━━━━━━━━━━━┛
\ (•‿ •) /
\ /
——
| |
|_ |_

& more

[Muskan Jain @Muskanjain0401]

Just shipped https://t.co/tt58bDG0j7 with @edvardh1

it applies to jobs for you:

- every opening in one feed (32k+ and counting)
- auto-applies to 100+ jobs in minutes
- writes each screening answer to match the role
- remembers your whole profile so you never fill the same form twice (powered by @supermemory)
- set it up once, it does the rest.

try it free and make applying way less painful.

Demo soon…

[MAZE @remvze]

wtf this is crazy: https://t.co/BuSej7vL3W

[Soumitra Sharma @soumitra_sharma]

I realized too late in my career that we all need to learn sales, irrespective of our profession or vocation.

In 2019, after more than a decade of what would be normally called a successful career track (pedigree, logos, scale, $$$), I went back to the drawing board and started self-training myself in sales (& marketing too) from scratch.

I can vouch that every point in this top @hackernews post on “How to do sales?” is true, and amazingly distilled to its simplest essence.

So much so that I have printed it out, kept it on my desk, to be reviewed each day.

Btw, it’s a real travesty that top universities and early-career jobs hardly provide any practical sales skills or training to young talent. I have seen this both in the US and India, and it’s a major gap in our learning systems.

[Cursor @cursor_ai]

We're making Git hosting more reliable, performant, and scalable.

This post traces 20 years of Git infrastructure and explains how that history led us to design and operate our Git storage, Origin, as if it were a database.

https://t.co/UW7jHuItSX

[Luis Velasco @luisvelasco]

Hi! I’m an FDE at OpenAI, and we’re thinking about publishing some of our work and learnings in a series of technical blog posts. What would you like us to write about?

[. @sailorsRest1]

Depictions of ancient Egyptian gardens

[kepano @kepano]

@kentdebruin I collected 70 different moats, and they're all still relevant
https://t.co/AnpR9P3bV6

[Suraj Gaud @notsurajgaud]

introducing fanout,

the everything learning app for engineers, curated by people building at the frontier.

your career has no fixed curriculum. neither does fanout.

become an ai researcher, a systems engineer, or find your own niche, fanout is a living archive of everything worth learning to become a better engineer.

[Ian Johnson 🔬🤖 @enjalot]

when I saw this dataset I knew I had to UMAP it!
in addition to the included embeddings, I also extracted vision latents from Marlin-2B for each clip.
getting everything rendering smoothly in the browser was also a mix of fun tricks. interactive map and writeup linked below 🎥

[Mannay 🌹 @mannay]

Generative Antitecture.

This is not a house.
This is automatic architecture.

// vanilla javascript

[Remotion @Remotion]

Better skills for better videos!

Remotion Skills 2.0:
• Sub-skills
• Interactive
• Taste-neutral

[Holly Blake @hollycurates]

the Pulverer Collection of Japanese illustrated books genuinely feels like finding a treasure trove every time i go there. go have a look, you will not regret it

1/ Miyako mon hyakka
Adachi Shinsoku, 1891
https://t.co/97FQ1e3AwV

2/ Banshoku zukō, Vol. 3
Katsushika Taito II, 1827
https://t.co/Ee6dP133Kg

3/ Date moyō hanazukushi
Furuya Korin, 1905
https://t.co/Wd66kRVijN

4/ Matsuzukushi, Takezukushi, Umezukushi
Furuya Korin, 1905–1906
https://t.co/Jqylh9uaqV

[Ian Bach ☯︎ @Ian8ach]

a little weekend sketch come to life... https://t.co/s3TRhfF23H

[Aaron Francis @aarondfrancis]

A good way to audit your codebase:

• a strong orchestrator inventories every subsystem
• it sends fresh read-only agents through with a DSA prompt
• it validates, dedupes, and ranks

I ran this overnight and it found 93 opportunities across 55 subsystems! Audit only.

[Tyler Angert @tylerangert]

I love this kind of stuff

I’ve been increasingly interacting with my codebase like this

The issue is that these visuals take a long time to make (even 10 minutes is too long)

A large part of the tokens spent to generate this is getting a model to understand structure, dependencies, connections between parts of the codebase

And if the codebase changes significantly you have to have models (often expensively) go and reanalyze the code and rebuild the visuals (and often verify that the visuals actually accurately reflect the code! Especially for things like simulated data flow)

So we need way more fast and deterministic tools for extracting out codebase structure that can be used as input for other tasks, as well as better “auto data viz” tools