Georeactor Blog

RSS Feed

Starting Tiny with Protein LLaMA

Lemon Wedges

the F-35 program makes us look back at the B-2

HBO's Palace Intrigue Flop

Regime review

Deep Sea Vent Deep Dive

Preparing the quinoa ML model

A recipe and a dive into polyploidy

Protein similarity Matryoshka Embeddings

Gene annotation corpora

UniProt

Could there be a Pandan emoji?

Matryoshka Embeddings?

Search on long sequences

Topics in Malay language

Kampung, Peranakan, Beka Melayu

2024 Travel Reads Part 2

EU foreign policy, and Japanese performance art

Seeing like a State-less Person

Ignore Previous Instructions and 𝑥_2

ML updates from the road

Revisiting 'Which Wiki Edit'

2024 Travel Reads

The French Foreign Legion and Madagascar

Catch-up with the SDXL ecosystem

Testing out image gen, LoRA, ControlNet

Sark Emoji Episode 7 - Did you mean Shark Emoji

Herbert's Hidden History Part 1

HyenaDNA, scGPT, and Mamba in CoLab

Alternatives to AgroNT

Census API Update

You Wouldn't Download a Quinoa

AgroNT and plant genomes

Trying out a Plant DNA LLM

AgroNT

Revisiting the Cryptic Lineages

Resolving an epidemiology mystery from 2022

Ignore Previous Instructions and 𝑥

Replacing ML Arxiv Haul

Reading Blog - December 2023

The Malay Archipelago

Bucket List Progress in 2023

500 words

Awkwafina was Nora from Queens

When one TV show ends...

Genomically Recoded Organisms

ML Arxiv Haul #27

22 new ML papers

Reading Blog - November 2023

Not this month

Iterating on CSS with GPT-4 and Puppeteer

Adventures in RTL layout

Amtrak story - the Congresswoman

from the Northeast Regional

ML Arxiv Haul #26

17 new mostly-ML papers

Kurdish parentheses on OpenStreetMap, Three Ways

Fixing a street name takes a detour

Eye ML - Training Eyegazer model

Podcast Recommendations Part 10

TV, medicine, and nonproliferation

Reading Blog - October 2023

China, the US, and Chicago in history

ML Arxiv Haul #25

12 new ML links and comments

Australia's not-Lyme illness

ML Arxiv Haul #24

15 or 16 new ML links and comments

Topics I would read a deep dive on

Variety of random questions

Word-edit tracing on Wikipedia

Microaggression in new articles

ML Arxiv Haul #23

23 new ML papers and comments for 23rd edition

Reading Blog - (Late) September 2023

Peace, Conservation

Cartoon ML - Part 5 - IDEFICS

Multimodal with a new HuggingFace model

Reading Blog - September 2023

History and Newark schools

Work on Jais and mGPT

More quantized models, and evaluating Indonesian

Edu updates - WGU and Duolingo

Savvy Code LLaMa ideas

QLoRA, Code LLaMa tests, and mGPT

Savvy LLM for NYC

GPT-NYC upgrade

ML Arxiv Haul #22

22 new ML papers and comments for 22nd edition

Eye update 👍

Reading Blog - August 2023

International justice and Congress

Fine-tuning savvy LLMs

Now that LLaMa v2 weights are available with a license agreement, development on Vicuña and other models updated.

Sark Emoji Episode 6 - The Bureaucracy Abides

Stay tuned for Unicode 16.0

After the Fire

Chicago, the series

Reading Blog - July 2023

Chicago, museums, and jury nullification

ML Arxiv Haul #21

More, mostly recent ML papers and comments

An unexpected dive into fundus photography and ML

Can computer vision tell a choroidal nevus from a melanoma?

ML Arxiv Haul #20

17 more ML papers and comments

Reading Blog - June 2023

Amnesia and biotech and Muppets

Froot of the Algorithm

People in the Mandela Effect community are also excited about AI.

Aliens of Arxiv #3

AI is trending lately, and not just here on Earth

Sitemap and Robots

Getting the site indexed

Cartoon ML - Part 4 - InstructBLIP describes cartoons

Progress with InstructBLIP model, prompting, multiple choice

ML Arxiv Haul #19

Another 17 ML papers and comments

Sark Emoji Episode 5 - Re-petition

the Unicode 15.1 beta

Reading Blog - May 2023

Global foods, future SCOTUS

Cartoon ML - Part 3 - Get your own Vicuna

Using Salesforce's new InstructBLIP model

Cartoon ML - Part 2 - Progress on Multiple Choice

Finding code examples to train a multiple choice model

ML Arxiv Haul #18

A new installment of ML papers and comments

Reading Blog - April 2023

Museums, Muslim travelers, and lentils

Sark Emoji Episode 4 - A New Note

If a new region falls in a forest...

ML Arxiv Haul #17

After a break, installment of ML papers and comments

Aliens of Arxiv #2

Von Neumann probes and other alien research updates

Fiction # Mobility

Trying something new! Was thinking about this world for a while.

Reading Blog - March 2023

Passenger pigeons, Russian barter, and new fiction.

Cartoon ML - Part 1 - BLIP

Trying basic image-captioning on the New Yorker cartoon contest dataset.

Semantic search and GPT NYC

Using a embeddings API and vector search DB as an alternative to generation

How does RLHF rank?

Where did RLHF come from, finding some datasets, and hot takes.

Sark Emoji Episode 3 - CLDR

CLDR added Sark. What's next?

Reading Blog - February 2023

Travelers in Greenland, nomad history, and a mysterious prophet

Podcast Recommendations Part 9

Books, hobos, Havana Syndrome, and architecture school

ML Arxiv Haul #16

Another installment of ML papers and comments

Flag of Sark Emoji - The High Council

An encouraging update on Sark from the Unicode Technical Committee and Emoji Subcommittee

Reading Blog - January 2023

From Greenpeace to GMOs, and Kazakh autobiography pt. 2

Where do flag Emoji and TLDs come from?

Alderney and Sark case study - crown dependencies, CLDR, etc.

ML Arxiv Haul #15

Next installment of 20 ML papers and comments

ML Arxiv Haul #14

New installment of ML papers collection

Now with Topics

Added topic pages to the blog (and RSS)

Google Maps Review Tags

Quirk of the Google Maps review tag in Japan

Starting Line

Test of the blog and RSS