devstein

Thanks, good to know! I'll add support as soon as I can.

Here is an issue for tracking: https://github.com/shared-recruiting-co/shared-recruiting-co...

I use https://wakatime.com/, which is great if you are a dev and want to get a weekly summary of how you spent your time

Right now the app only supports Gmail, so I've limited login to only Google. I'm working on changing this soon!

What email provider do you use?

In my opinion, it's always good to be regularly interviewing and talking to other companies. I don't think the job search process should be so binary.

Start talking to other companies, reply to some recruiting emails that interest you, etc. It doesn't mean you have to leave you current position, but talking to other companies forces clarify what you are really looking for in your job and potential next opportunity. It also helps you get a sense of what other companies are looking for if you end up deciding the time is right for something new.

I'm trying to use GPT to help me (and others) manage recruiting emails and the job search process.

Right now, every time you start looking for a job, you start from scratch. Review old emails, search for relevant job boards, check HN, check LinkedIn, etc. The goal is to use GPT to automate outbound to companies to find you potential opportunities that match your preferences. Basically a GPT-powered recruiter for every candidate. Similar to what companies currently do with tools like Gem, but giving the power back to candidates.

https://github.com/shared-recruiting-co/shared-recruiting-co

A Foundation Model Primer

The pace of progress in artificial intelligence right now is incredibly exciting. Large, pre-trained foundation models like GPT4, Claude, LLaMA, Stable Diffusion, and similar are disrupting everything from search to protein folding to all categories of design. We suspect these models will become integral parts of the vast majority of products over time, analogous to how relational databases are ubiquitous components of virtually all applications.

However, it can be difficult to keep up with what is happening in this market given how fast it is moving. What are all the emerging use cases? What is the state of research in this space? How are foundation models actually built into applications? What are some of the common challenges faced by teams productizing foundation models?

We recently put together an internal presentation for the investing team at Innovation Endeavors to answer a lot of these questions. While a lot of resources exist online regarding foundation models, we had not seen a comprehensive overview of the space like this, so we wanted to share it externally in case others found it useful.

An impressive open source framework for custom building retrieval based ChatGPT plugins. Highlights are:

"A notable feature of the Retrieval Plugin is its capacity to provide ChatGPT with memory. By utilizing the plugin's upsert endpoint, ChatGPT can save snippets from the conversation to the vector database for later reference (only when prompted to do so by the user). This functionality contributes to a more context-aware chat experience by allowing ChatGPT to remember and retrieve information from previous conversations. Learn how to configure the Retrieval Plugin with memory here."

"The Retrieval Plugin is built using FastAPI, a web framework for building APIs with Python. FastAPI allows for easy development, validation, and documentation of API endpoint"

This is awesome! Well done and thanks for sharing. Just subscribed :)

I'm actually working on something similar, but specific to inbound job opportunities (Email and LinkedIn). The goal is to use GPT to parse unstructured, unstandardized jobs into a structured, standardized job format that makes it easy for candidates to search and review once they start their job search.

It's in it's early stages, but you can check it out here and let me know what you think: https://sharedrecruiting.co/

I'd love to chat about more about this if you up for it! You can reach me at team at sharedrecruiting.co

Good to know, thank you!

I agree. I think it's common for people to start with the shotgun approach to build confidence interviewing then start sniping a few dream roles as they start to get further along with the shotgun companies

Sorry to hear your job search has been rough :( the lack of transparency in the interview process is a real problem (i.e getting ghosted by companies) .

I'm working on a product to make the transition from happily employed -> actively looking as easy as possible for candidates by creating a personalized job board of companies interested in you while you aren't looking. Once you are actively looking, I'm trying to address the transparency issues via communication SLAs and automation.

It's in the super early stages, but you can check it out here: https://sharedrecruiting.co/

Let me know if this resonates/what you think!

Do you have source of truth for if that job is still active? For example, is the job description still publicly visible from your ATS (Greehouse, Lever, etc)

I asked because I've been thinking about this problem with job boards. Job boards often duplicate job description information rather than relying on the original JD in the company's ATS.

> I got "The connection has timed out" which could be your problem. If your hosting is unreliable that's the kiss of death.

Interesting...I haven't had that issue before. I'm using Deno Deploy for hosting, which is nascent, so it's possibly less reliable than I realize.

Thanks for the SEO advice, makes sense. I'll keep in mind the incremental page rollouts for next time.

I'm curious do you know if low SEO (no external links, etc) impacts Google's willingness to index it? Or does it only impact it's ranking in search results?

What type of spam are you getting?

Gmail is pretty solid. For the emails it misses, you can mark them as spam and it rarely misses similar emails again.

> We tried some new tactics near the end that seemed to be bearing fruit, and I think in a world where tech hadn't crashed in mid to late 2022 we would have had a reasonable shot.

Is this referring to Magnet? I thought that was neat product idea.

I built YCRM (https://ycrm.xyz/) as a tool to help me get in touch with YC founders for user research to validate B2B SaaS ideas!

It's been surprisingly successful with other B2B startups.

Not enough revenue to be my main source of income, but it's a nice monthly bonus.

The Shared Recruiting Co. (SRC) is an open-source, candidate-centric recruiting platform. SRC makes recruiting more efficient and less painful by promoting transparent, opt-in communication between candidates and companies.

For candidates, SRC is an AI-power inbox assistant that manages your inbound job opportunities while you aren't looking for a new role and supercharges your job search once you are.

For companies, SRC is a sourcing sidekick that helps you find the right candidates at the right time without spamming them without follow-up emails.

I remember reading this article a few years back and thought it was a great idea.

Does anyone know if it was successful? Do they still do it?

I'm working on a tool for candidates to make the transition from "not looking" to "actively looking" for a job easier. It plugs into your email and leverages your historic inbound opportunities to jumpstart your job search.

It's still invite-only, but check it out at https://sharedrecruiting.co/ and let me know what you think!

I agree. Requirements have become somewhat meaningless.

What do you think could improve that? Maybe requiring employers to write 1-2 line s justifying the requirements?

I've been working on using OpenAI to manage (organize, auto-respond, etc) my inbound recruiting emails. I think the same could be applied to sales emails.

It's been a ton of fun. I'm basically using AI automation to fight AI automation :)

You can follow along at: https://sharedrecruiting.co/

I maintain several open source projects, most notably:

Sparkmagic (https://github.com/jupyter-incubator/sparkmagic)

Sparkmagic provides jupyter magics and kernels for working with remote Spark clusters. It's used by thousands of developers and companies like Pinterest, Amazon, more!

I've been maintaining for the past few years and would love help!

KSOPS (https://github.com/viaduct-ai/kustomize-sops)

KSOPS, or kustomize-SOPS, is a kustomize KRM exec plugin for SOPS encrypted resources. KSOPS can be used to decrypt any Kubernetes resource, but is most commonly used to decrypt encrypted Kubernetes Secrets and ConfigMaps. As a kustomize plugin, KSOPS allows you to manage, build, and apply encrypted manifests the same way you manage the rest of your Kubernetes manifests.

KSOPS is the most popular kustomize plugin and I'd love help maintaining and improving it from out GitOps fanatics.

It's an incentive misalignment. Third party recruiter optimize for their contingency fee. The goal of their emails is to peak your interest enough to get you on the phone, so they can pitch you one or many of the companies they are working with. There is no incentive for them to disclose all the information upfront.

I'm actually in the very early stages of a product to better align incentives and promote transparency between candidate and recruiters. If you're interested, you can get updates at: https://sharedrecruiting.co/

Feedback and thoughts are welcome!

Couldn't agree more! I'd love to chat more about this. Just sent you an email :)

No, I logged into my Amazon account. I’m curious how they are storing my credentials or access token.

Great post and intuitive visuals! I recently had to rack my brain around UTF-8 encoding and decoding when building the Unicode ETH Project (https://github.com/devstein/unicode-eth) and this post would have been very useful