News for hackers. Stuff that matters.

devxpy

Re:LLMs Aren't World Models on Wednesday August 13, 2025 @07:22AM (#44887096)
I don’t think you even need such complex tests as chess to see it doesn’t have a world model - just ask it to do any 5+ digit multiplication
Hi Peter! Heard your name from a couple of friends who have gotten their visas from you! Nice to see you here.

What kind of travel restrictions apply for someone on an O-1 visa (potentially looking to file for EB-1A)? Is there a recommended minimum period of stay in the US?

The main issue is that its very slow and expensive to browse the internet like this. The LLM will only perform well if you have it do chain of thought reasoning, and that has a latency hit because of a longer generation.
Re:Google agrees to invest up to $2B in OpenAI rival Anthropic on Saturday October 28, 2023 @07:55AM (#38049124)
I’ve just the thing for you my friend https://github.com/devxpy/anti-chatgpt
Re:Ask HN: Who is hiring? (July 2023) on Monday July 03, 2023 @01:05PM (#36575861)
Gooey.AI | Full Time | REMOTE / ONSITE | Seattle & Bengaluru | http://gooey.ai/

We are building a GenAI platform that abstracts all the latest LLMs, animation tools, speech reco, etc from OpenAI, Stability, Google, Meta, etc. One of our projects - https://farmer.chat - was demoed at the UN General Assembly in April 2023.

You'll be the 2nd engineer alongside me - https://github.com/devxpy

Anyone with experience building developer platforms, no-code solutions, pretty UIs, AI models, k8s GPU clusters, prompt engineering, reach out!

Here's a list of models we currently feature, they're pretty cool! - https://gooey.ai/explore/

JD - https://www.help.gooey.ai/jobs/senior-software-engineer

Email - [email protected]

Re:It's React, but in Python on Thursday June 08, 2023 @05:59AM (#36239424)
Don't use pickle. Use JSON for stuff you can't represent in HTML forms.

For database connections, large datasets, etc (stuff you can't send off to the browser) use redis.

This is a trade-off between DX and UX. Holding session state means you need sticky session routing, and restarting servers kills your user's sessions. Plus imposing a websocket on your users is a cardinal sin, makes scaling incredibly hard, makes page load times abysmal, makes disconnects a nightmare for both you and your user.

Its fine if you're creating something like stable diffusion web ui though, which is meant to be a single user app.

Re:It's React, but in Python on Wednesday June 07, 2023 @05:01AM (#36224529)
The way to solve session management is to just store the state in html forms and send it back to a stateless http endpoint. That way you get a website that behaves the way all websites work, and can scale easily.
Re:Reflected Diffusion Models on Monday May 08, 2023 @02:02PM (#35864907)
Is there a way to run this locally?
Creating the index on pinecone takes about a minute. Creating a table on postgres should take a few milliseconds!
Re:The GPT Architecture, on a Napkin on Sunday December 11, 2022 @08:52AM (#33943158)
Would also love this to include InsturctGPT architecture with its RL reward model!
Re:Ask HN: Who is hiring? (December 2022) on Thursday December 01, 2022 @05:11PM (#33823672)
Gooey.AI | Full Time | REMOTE / INTERNS / ONSITE | Seattle & Bengaluru | http://gooey.ai/

We're building a Generative AI no-code platform. Think Zapier, but for Software 2.0

Anyone with experience building developer platforms, no-code solutions, pretty UIs, AI models, GPU orchestration, please reach out!

Here's a list of recipes we currently feature, they're pretty cool! - http://app.gooey.ai/

Email - [email protected]

Re:Show HN: Stable Diffusion v2 web interface on Thursday November 24, 2022 @05:08PM (#33736791)
Yeah, seems like its been hugged to death a bit. A single GPU is not quite enough.

Completes in around a minute for me right now

Re:Show HN: Stable Diffusion v2 web interface on Thursday November 24, 2022 @04:04PM (#33736205)
Shameless plug - We don’t require logging in!

https://app.gooey.ai/CompareText2Img/?example_id=1uONp1IBt0Y

Re:Stable Diffusion 2.0 Release on Thursday November 24, 2022 @11:40AM (#33733281)
Re:Stable Diffusion 2.0 Release on Thursday November 24, 2022 @05:09AM (#33729581)
Fixed. Thanks for reporting.

Here's the bug that caused this too - https://bugzilla.mozilla.org/show_bug.cgi?id=1689099

Re:Stable Diffusion 2.0 Release on Thursday November 24, 2022 @04:54AM (#33729496)
Hmm, looks like we didn't test on Firefox!
Re:Stable Diffusion 2.0 Release on Thursday November 24, 2022 @04:47AM (#33729446)
I've also built a similar service[1] that does this with inpainting instead of textual inversion, so it preserves the face exactly and returns in seconds, not hours.

[1] - https://app.gooey.ai/FaceInpainting/

Re:Show HN: Create art from your face using Stable Diffusion on Monday October 10, 2022 @06:53PM (#33157360)
Thanks, this is helpful!
Re:Show HN: Create art from your face using Stable Diffusion on Monday October 10, 2022 @06:50PM (#33157335)
It does the masking automatically by doing face recognition.

That's why the mask and cutout are part of the output too!

Re:Show HN: Create art from your face using Stable Diffusion on Monday October 10, 2022 @05:13PM (#33156451)
By others do you mean the people whose code/models I'm using?
Re:Show HN: Create art from your face using Stable Diffusion on Monday October 10, 2022 @05:05PM (#33156378)
Added.
Re:Show HN: Create art from your face using Stable Diffusion on Monday October 10, 2022 @04:58PM (#33156311)
Adding a privacy policy. "not that it would help much" -- Any ideas on what would help much?
Re:AWS vs. GCP reliability is wildly different on Thursday September 22, 2022 @03:30AM (#32935771)
Oh interesting. Which region and GPU type were you working with? (Asking so I can avoid in future)
Re:AWS vs. GCP reliability is wildly different on Wednesday September 21, 2022 @05:29PM (#32931754)
Is this testing for spot instances?

In my limited experience, persistent (on-demand) GCP instances always boot up much faster than AWS EC2 instances.

Re:Ask HN: Who is hiring? (August 2022) on Monday August 01, 2022 @02:54PM (#32310537)
https://dara.network/ | Senior full stack engineer | Full time | Remote (Anywhere) or Onsite (Bangalore, India)

We're on a mission to build communities for changemakers. Our app, Dara is already used by thousands of the best artists, change makers and institutions in the world to connect to each other and their alumni. Dara is inspired by the need for all of us - but especially those trying to make change - to have a safe, private digital space to discover the best work and communicate authentically within our communities.

Tech stack - You’ll be working with Flutter (Dart) as our primary client side language and Python (Django) on the server. We also use HTML/JS/CSS for rendering SEO content, and of course host our own servers for everything.

Perks - Flexible working hours (except 1 daily standup) + office setup budget + health insurance We’re also very small (2 engineers) so you get tons of autonomy.

Get back to me at https://dara.network/dev/ with your coding superpower, and we'll continue the conversation there.

Looking forward to hearing from you :)

Re:Vite – Next Generation Front End Tooling on Sunday July 03, 2022 @12:40PM (#31969007)
Try flutter, its a breath of fresh air!
Re:Ask HN: Who is hiring? (July 2022) on Friday July 01, 2022 @05:20PM (#31953108)
https://dara.network/ | Senior full stack engineer | Full time | Remote (Anywhere) or Onsite (Bangalore, India)

We're on a mission to build communities for changemakers. Our app, Dara is already used by thousands of the best artists, change makers and institutions in the world to connect to each other and their alumni. Dara is inspired by the need for all of us - but especially those trying to make change - to have a safe, private digital space to discover the best work and communicate authentically within our communities.

Tech stack - You’ll be working with Flutter (Dart) as our primary client side language and Python (Django) on the server. We also use HTML/JS/CSS for rendering SEO content, and of course host our own servers for everything.

Perks - Flexible working hours (except 1 daily standup) + office setup budget + health insurance We’re also very small (2 engineers) so you get tons of autonomy.

Get back to me at https://dara.network/dev/ with your coding superpower, and we'll continue the conversation there.

Looking forward to hearing from you :)

Older »