News for hackers. Stuff that matters.

henrysg

Show HN: Shepherd – open-source tools to manage self-hosted software deployments

https://trustshepherd.com/

Hey HN, I wanted to share something I’ve been working on. My startup previously built B2B SaaS, and large enterprises sometimes wanted to self-host it for data residency reasons - but this was a nightmare to build and support. I chatted to other builders/founders and it seems this pain is pretty common. But people tolerate it because the biggest customers often require self-hosting.So we’ve...

( Read More... | no comments | 4 points | on HN )
Re:SOC2 compliance is a waste of time on Monday January 13, 2025 @12:13PM (#42685791)
Totally agree
I agree, customer-managed self-hosted is definitely more common. I have seen more discussion recently of vendor managed as a middle ground, often called BYOC
Nice launch - congrats!
Re:Show HN: LinkedIn Hype Crew on Thursday October 17, 2024 @04:12AM (#41867455)
You can request account deletion by emailing legal at context dot ai, we have a process for this
Re:Show HN: LinkedIn Hype Crew on Wednesday October 16, 2024 @03:19PM (#41862788)
Totally agree! Its frustrating how hard it is to get profiles from LinkedIn. You can send any resume - a regular PDF, or a LinkedIn download
Re:Show HN: LinkedIn Hype Crew on Wednesday October 16, 2024 @03:18PM (#41862774)
Thank you!

Show HN: LinkedIn Hype Crew

Hi HN - we’ve been working on a fun project that I wanted to shareIt takes your PDF LinkedIn profile or resume and generates a short podcast either hyping you up, or roasting you.It takes your professional experience and crafts a narrative of your life and why you’re so successful. Or if you want a roast… It pokes holes and makes fun of you.I’d love to hear any feedback!https://podial.ai/hype

( Read More... | 19 comments | on HN )
Re:Swarm, a new agent framework by OpenAI on Saturday October 12, 2024 @02:04PM (#41821070)
Isn't their project called Swarm and yours called Swarms?

Show HN: Podial – Generate engaging educational podcasts from any documents

Today we’re launching Podial - it lets anyone generate engaging podcasts to learn any topic and from any documentsWe think generative podcasts are a breakthrough in user experience for LLMs. Turning anything into a podcast discussion works really well - it's engaging, fun, and it's particularly great for learning. Even Andrej Karpathy agrees -...

( Read More... | no comments | 5 points | on HN )
Re:Mistral "Mixtral" 8x7B 32k model [magnet] on Friday December 08, 2023 @04:41PM (#38574886)
> Oddly absent: an over-rehearsed professional release video talking about a revolution in AI.
Re:Ask HN: Tooling to Improve LinkedIn Messaging? on Thursday December 07, 2023 @10:56AM (#38557780)
Thanks for the suggestion. I'm not looking for a CRM-like replacement of LinkedIn, I just want a Chrome Extension to make the existing LinkedIn messaging product better

Ask HN: Tooling to Improve LinkedIn Messaging?

I'm looking for a tool to make LinkedIn messaging suck a little less. Particularly snoozing messages and no-reply reminders (yes I get ghosted a lot)GetDabble looks perfect but has no reviews https://getdabble.ioAnyone found anything good here?

( Read More... | 3 comments | on HN )
Thank you!

Show HN: Codebasechat.com – Make a GPT chatbot for any GitHub Repo in 30 seconds

Hi HN - I’m excited to share a fun side project we built recentlyCodebaseChat.com is a tool for building a GPT chatbot for any GitHub repo in 30 secondsIt can be helpful when onboarding to new codebases, when needing help understanding system design, asking for less technical explanations of functionalityWe’ve been heads down building Context.ai, the analytics platform for LLM products. When...

( Read More... | 2 comments | 4 points | on HN )
Re:Attenuating Innovation (AI) on Wednesday November 01, 2023 @02:54PM (#38103116)
Fantastic paragraph:

"The point is this: if you accept the premise that regulation locks in incumbents, then it sure is notable that the early AI winners seem the most invested in generating alarm in Washington, D.C. about AI. This despite the fact that their concern is apparently not sufficiently high to, you know, stop their work. No, they are the responsible ones, the ones who care enough to call for regulation; all the better if concerns about imagined harms kneecap inevitable competitors."

Older »