Hacker News: aleksanderhan

New comment by aleksanderhan in "Show HN: Turbo-Genius"

aleksanderhan — Thu, 06 Jun 2024 19:49:26 +0000

Turbo-Genius just got image capabilities. Still early days, but I'm planning on implementing this paper: https://arxiv.org/abs/2303.04671 - only with local models.

Show HN: Turbo-Genius

aleksanderhan — Wed, 05 Jun 2024 10:39:16 +0000

Just another streaming llm server and client for local huggingface transformers models.

Comments URL: https://news.ycombinator.com/item?id=40583407

Points: 1

# Comments: 1

New comment by aleksanderhan in "Ask HN: Who wants to be hired? (June 2024)"

aleksanderhan — Mon, 03 Jun 2024 21:42:44 +0000

Location: Oslo

Remote: Yes

Willing to relocate: Yes

Technologies:

  Languages: Java, Python, Typescript

  Frameworks: Spring Boot, Flask, FastApi, transformers, langchain

  Databases: Postgresql, MySql

  Cloud: AWS

Résumé/CV: https://www.linkedin.com/in/aleksander-hansen/

Email: aleksanderhan [at] gmail [dot] com

Website: http://app.algobase.ai

New comment by aleksanderhan in "OpenAI's board has fired Sam Altman"

aleksanderhan — Fri, 17 Nov 2023 23:12:36 +0000

>Mr. Altman’s departure follows a deliberative review process by the board, which concluded that he was not consistently candid in his communications with the board

>In a statement, the board of directors said: “OpenAI was deliberately structured to advance our mission: to ensure that artificial general intelligence benefits all humanity. The board remains fully committed to serving this mission

>OpenAI was founded as a non-profit in 2015 with the core mission of ensuring that artificial general intelligence benefits all of humanity

This suggest to me that he was trying move them away from the mission of creating AGI and instead focus more on profits

A Programatical Ode to Galileo

aleksanderhan — Tue, 19 Sep 2023 21:27:08 +0000

Article URL: https://github.com/aleksanderhan/ode-to-galileo

Comments URL: https://news.ycombinator.com/item?id=37576993

Points: 1

# Comments: 0

New comment by aleksanderhan in "Jupyter AI"

aleksanderhan — Mon, 07 Aug 2023 13:08:23 +0000

I made something similar just for fun: https://github.com/aleksanderhan/labpilot It seems Jupyter is perfect for these kinds of code assist tools. Instead of going to Wikipedia and scratching your head about how this algorithm worked again, you can just mention what you want and have a rough/good enough implementation in no time.

Show HN: Labpilot – comment driven development with Jupyter lab

aleksanderhan — Thu, 03 Aug 2023 19:17:33 +0000

Hello,

I've been working on this project of mine these last couple of months, and with the release of Jupyter AI, I just had to go ahead and release my own project into the wild.

I call the paradigm, "comment driven development". You use special comments, "#@" in the notebook cells, to steer the LLM to write the code you need. Got a bug in your code? - The debug feature takes the stacktrace and fixes the code for you. It also has a explain feature if some of the code is hard to understand.

I'm also working on a more experimental "autogpt" feature that can be accessed from the Labpilot terminal, which is built into Jupyter lab.

It's been really fun to build and play with. I hope somebody will find it useful. I appreciate any feedback I can get. Thank you.

Comments URL: https://news.ycombinator.com/item?id=36990430

Points: 1

# Comments: 0

New comment by aleksanderhan in "OpenAI’s policies hinder reproducible research on language models"

aleksanderhan — Thu, 23 Mar 2023 12:10:12 +0000

Nobody are forced to anything. You don't have to use openai services if you don't want to...

New comment by aleksanderhan in "Ask HN: What's the largest amount of bad code you have ever seen work?"

aleksanderhan — Wed, 14 Nov 2018 17:21:04 +0000

Sounds like a way an reinforcement learning algorithm could write code.