@mgorinova
Shaping the future of programming @tessl.io 🚀 | ex-@TwitterCortex @Birdwatch 💙 | PhD in probabilistic machine learning, loyal servant to a cat, collector of random variables, and lover of well-placed puns. https://mgorinova.github.io/
Learn more about our work on abstraction adherence of coding agents! www.youtube.com/watch?v=nx5_...
#coding #aicoding #agenticai #codegen #devtools #cursor #claudecode
Had such a great chat with @sjmaple.bsky.social about abstraction adherence of coding agents, as well as what matters when it comes to evaluation. Check it out in the new @ainativedev.io podcast episode!
YouTube: ainativedev.co/ble
Apple Podcasts: ainativedev.co/exx
Spotify: ainativedev.co/2mn
At the risk of starting the flame war to end all flame wars...
Modern LLMs (GPT-5.1, Claude 4.5, Gemini 3) produce excellent code and can be a significant productivity boost to software engineers who take the time to learn how to effectively apply them - especially if used with coding agent tools
Build AI tools for community growth at our hackathon with Lovable & Led By Community
One day to collaborate with developers, designers, and community builders. Focus on real problems: onboarding, engagement, moderation, and events.
📅 Dec 3rd, 9 AM-5 PM
📍 Tessl HQ, London
luma.com/ai-hackathon...
Super excited to share what we've been doing at @tessl.io to improve the quality of code generated by AI agents! 🤖
We introduce a new way to measure abstraction adherence and show how Tessl's usage specs significantly boost it.
Check out the full article!
tessl.io/blog/propose...
It's funny to me how British digital newspapers are crying out loud what an invasion of privacy a state-issued digital ID is, but force me to accept tracking cookies or pay a fee.
"I really need a tool that helps me count the number of letters in 'blueberry'. It will change my life."
... said no one ever.
I stole this for the linkedin post 😂 Gratitude 🫡
Aaaaaaa! I'm regretting my choices 🥲
I actually like the em dash. Am I an LLM? 🤔
A chatgpt generated take on the iconic kiss on the Berlin wall. But with Elon Musk kissing the Twitter blue bird. The text reads "My God, help me survive this tweet love"
A few years late but I was finally able to generate this
Wait... So s1 cost only $50 to fine-tune and beat o1-preview. And the secret sauce is... forcing the model to generate "Wait" instead of end-of-sequence???
Ahahhahahhaha this is so cool
🚨 MAJOR ALERT 🚨
The people wanted verification badges on Bluesky and @guan.dk and I have teamed up to bring you verification badges.
Behold! It is the Official Verified Labeller!
bsky.app/profile/veri...
Strong characters sounds amazing + I think there is a lot to learn from that time if portrayed well. Thanks for the recommendation, I will give it a go!
Hi John,
That’s what all the bots say 😳😂
Not really my area of expertise, I know of the very obvious ones like input sanitation, regular finetuning on problematic examples, etc. The folks at lakera.ai have been on it for some time and regularly host hacking challenges, which I enjoy following
I love Silo and For All Mankind. Maybe I should try Halt & Catch Fire next!
Thank you! Indeed, what a debacle 😂 🍿
What's the drama with Byzantine? Did someone raise it during reviewing in the past? Is there a public discussion? 🍿
Bluesky's firehose is a treasure trove of public data for researchers and developers, and it's completely free. Check out our developer docs: docs.bsky.app
Book outline
Over the past decade, embeddings — numerical representations of machine learning features used as input to deep learning models — have become a foundational data structure in industrial machine learning systems. TF-IDF, PCA, and one-hot encoding have always been key tools in machine learning systems as ways to compress and make sense of large amounts of textual data. However, traditional approaches were limited in the amount of context they could reason about with increasing amounts of data. As the volume, velocity, and variety of data captured by modern applications has exploded, creating approaches specifically tailored to scale has become increasingly important. Google’s Word2Vec paper made an important step in moving from simple statistical representations to semantic meaning of words. The subsequent rise of the Transformer architecture and transfer learning, as well as the latest surge in generative methods has enabled the growth of embeddings as a foundational machine learning data structure. This survey paper aims to provide a deep dive into what embeddings are, their history, and usage patterns in industry.
Cover image
Just realized BlueSky allows sharing valuable stuff cause it doesn't punish links. 🤩
Let's start with "What are embeddings" by @vickiboykis.com
The book is a great summary of embeddings, from history to modern approaches.
The best part: it's free.
Link: vickiboykis.com/what_are_emb...
💯 no fake science please 😬😬😬 This sort of accounts can also be used to build up a following base and then activate as part of an influence campaign
Personally, I like Quiet Posters: it surfaces posts I wouldn't have seen otherwise!
By the authority vested in me by the decentralised gods (💅🏻) I accept this proposition.
(💅🏻 Sarcasm. I possess no such authority. The decentralised gods would never grant it to me (💅🏻))
Maybe we need a special sarcasm tag here on bsky
My question was a joke!
I know what the word means 🤣
What do you mean "once"? 🤨
