Alexey Geht

Senior Talent #Sourcer 🔎 @AddedValue #Yogi 🧘 #Boolean developer 🖲 Amature Gardener 🍆🥕🌽 and a #DigitalNomad 👨‍🚀. opinions are my own.

[Alexey Geht @GehtAlex]

Hey Twitters!

Just posted a short article about approaching tp-notch SW Developers in a highly competitive market 🤓

https://t.co/bOf3N6G903

Enjoy!

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Hung Lee @HungLee]

Recruiting Brainfood - Issue 452
https://t.co/kvXqIecr7I

State of Talent Report 2025, Transformation of RPO's, the Return of Phrenological Appraisals, Grievance Doctrine of Trade and why GenAI content is our Polyester...

[Min Choi @minchoi]

Google just announced their massive AI update in Search.

Google will now Google for you.

Here's what you need to know:

[Tolga Bilge @TolgaBilge_]

Another two safety researchers leave: Ilya Sutskever (co-founder & Chief Scientist) and Jan Leike have quit OpenAI.

They co-led the Superalignment team, which was set up to try to ensure that AI systems much smarter than us could be controlled.

Not exactly confidence-building.

[Ilya Sutskever @ilyasut]

After almost a decade, I have made the decision to leave OpenAI.  The company’s trajectory has been nothing short of miraculous, and I’m confident that OpenAI will build AGI that is both safe and beneficial under the leadership of @sama, @gdb, @miramurati and now, under the excellent research leadership of @merettm.  It was an honor and a privilege to have worked together, and I will miss everyone dearly.   So long, and thanks for everything. I am excited for what comes next — a project that is very personally meaningful to me about which I will share details in due time.

[Alexey Geht @GehtAlex]

In observing sourcing email sequences that did or didn’t use Generative AI tokens, there’s a considerable (~46%) lift in reply rate for campaigns using AI personalization (35.3% vs 24.1%). Source: https://t.co/vtlq3GEVWg via @ashbyhq

[Hung Lee @HungLee]

Roles in AI, guide for recruiters

[Linus ✦ Ekenstam @LinusEkenstam]

Amazon got more than 750.000 robots deployed.

Most people don’t realize how fast the robotics industry is scaling

Amazon is the perfect candidate.

10 years ago, robots were practically non-existent in their global warehouse and distribution network.

But this is the actual acceleration ramp-up.

2013: 1,000
2014: 15,000
2017: 100,000
2019: 200,000
2021: 350,000
2022: 520,000
2023: 750,000

Let’s zoom in on the two last jumps.

400,000 additional robotic units in roughly two years.

That results in thousand of new units deployed *every week* 🚀

It’s clear. Beyond doubt. That AI, robotics, computer vision, will and is replacing a lot of human labor. And will continue accelerating that progress in the next decade.

It’s important to note that this will also accelerate the need for more high-skilled work. Make industry safer.

The biggest challenge we will face is the grandeur of re-skilling and up-skilling that will be facing the workforce in a relative short period of time ahead.

We’ve entered the Era of Robotics and The Age of Intelligence all at once.

[Alexey Geht @GehtAlex]

Building your own custom GPT. This is wild!

[Linus ✦ Ekenstam @LinusEkenstam]

Madness, @sama builds a custom GPT using private knowledge in just under 4 minutes.

Then he goes on to share it.

There will be millions of GPTs.

[Alexey Geht @GehtAlex]

לכל מי ששאל, חשב, ולא היה בטוח. מרדכי גלץ אחד המגייסים המוכשרים בארץ הקודש ייתן טיפים ששווים זהב. לרוץ ולהירשם. https://t.co/CfXDDuAsWs

[Alexey Geht @GehtAlex]

Great show, everybody!
Thanks to the Curator, @HungLee, at Recruiting Brainfood!

@Adam_W_Gordon Lauren Harrop Rebecca Collis Associate CIPD Anna Pokrzywka-Szklarska https://t.co/i6x6cgT3LT

[Alexey Geht @GehtAlex]

Recruiting Brainfood is now live on air; join us to hear more about imposter syndrome. https://t.co/0Uw71fDUOA

[Alexey Geht @GehtAlex]

a little bit off the topic :)
what is self care for you? https://t.co/2ZQbyz7YEt

[Alexey Geht @GehtAlex]

התמזל מזלי, ופגשתי לשיחה מאוד מעניינת את מוטי. דיברנו על סורסינג, גיוס, המעבר בין התפקידים ושאר הירקות. האזנה מומלצת לכל מי שנמצא בעולמות האלה.
Moty Geltz #sourcing #talentsourcing #recruitment #recruiter #startup #startupnation #hightech #podcast https://t.co/EROt2lU0Hv

[Alexey Geht @GehtAlex]

Recruiters/Sourcers! What do you think, to how many fake profiles did you reach out during your career?
#fake #profiles #linkedin https://t.co/O5Lrg9xfS0

[Alexey Geht @GehtAlex]

Exciting news! Our very own Shiri Horn Brezel just earned a coveted spot on Recruiting Brainfood from @HungLee, thanks to her latest article on Deep Learning Sourcing. We are incredibly proud of her and the entire team for continuously crafting amazing co…https://t.co/w09zJoEbWM

[Alexey Geht @GehtAlex]

Great article Shiri, Alufa! https://t.co/IBnc2iYEjs

[Alexey Geht @GehtAlex]

Humans aren't designed to be productivity machines! very nicely done ✔️ https://t.co/jWwAxZBN6U

[Alexey Geht @GehtAlex]

Wow, now this is super cool. https://t.co/GkdUCCccvi

[Alexey Geht @GehtAlex]

Now this is useful ladies and gentlemen 🙋‍♀️🏌‍♀️ https://t.co/QG3KOIHudK