Maria Gorinova
@mgorinova.bsky.social
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/
https://mgorinova.github.io/
Pinned
Maria Gorinova
@mgorinova.bsky.social
· Nov 20
A Proposed Evaluation Framework for Coding Agents: Specs Enhance Proper Use of Public APIs by ~35%
This article proposes an evaluation framework highlighting how specifications enhance coding agents' effective use of public APIs.
tessl.io
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...
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...
Learn more about our work on abstraction adherence of coding agents! www.youtube.com/watch?v=nx5_...
#coding #aicoding #agenticai #codegen #devtools #cursor #claudecode
#coding #aicoding #agenticai #codegen #devtools #cursor #claudecode
The Population Test Your Agent Must Pass | Maria Gorinova
YouTube video by AI Native Dev
youtube.com
December 16, 2025 at 1:52 PM
Learn more about our work on abstraction adherence of coding agents! www.youtube.com/watch?v=nx5_...
#coding #aicoding #agenticai #codegen #devtools #cursor #claudecode
#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
YouTube: ainativedev.co/ble
Apple Podcasts: ainativedev.co/exx
Spotify: ainativedev.co/2mn
December 9, 2025 at 3:47 PM
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
YouTube: ainativedev.co/ble
Apple Podcasts: ainativedev.co/exx
Spotify: ainativedev.co/2mn
Reposted by Maria Gorinova
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
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
November 27, 2025 at 7:55 PM
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
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
Reposted by Maria Gorinova
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...
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...
AI Lovable Hackathon London: Community Tools Edition · Luma
🧠 AI Hackathon: Community Tools Edition
Hosted by Led by Community
Powered by Lovable & Tessl
Join us for a hands-on hackathon to build AI-powered tools that…
luma.com
November 26, 2025 at 12:03 PM
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...
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...
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...
A Proposed Evaluation Framework for Coding Agents: Specs Enhance Proper Use of Public APIs by ~35%
This article proposes an evaluation framework highlighting how specifications enhance coding agents' effective use of public APIs.
tessl.io
November 20, 2025 at 3:18 PM
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...
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.
September 26, 2025 at 1:34 PM
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.
... said no one ever.
a raccoon laying on a bed with a bowl of blueberries in its mouth
Alt: a raccoon laying on a bed with a bowl of blueberries in its mouth; labelled "bluwbewwy"
media.tenor.com
August 10, 2025 at 8:38 AM
"I really need a tool that helps me count the number of letters in 'blueberry'. It will change my life."
... said no one ever.
... said no one ever.
I actually like the em dash. Am I an LLM? 🤔
August 3, 2025 at 8:55 AM
I actually like the em dash. Am I an LLM? 🤔
A few years late but I was finally able to generate this
May 26, 2025 at 5:46 PM
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
Ahahhahahhaha this is so cool
February 11, 2025 at 12:16 AM
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
Ahahhahahhaha this is so cool
Reposted by Maria Gorinova
🚨 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...
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...
bsky.app
November 26, 2024 at 4:24 AM
🚨 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...
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...
Reposted by Maria Gorinova
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
November 23, 2024 at 5:54 AM
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
Reposted by Maria Gorinova
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...
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...
November 22, 2024 at 11:13 AM
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...
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
BOOOO NOOOO BLOCK BLOCK BLOCK!!! This image is fake. Let’s not let fake science accounts thrive on Bluesky!!!
The Helix Nebula captured by NASA'S Hubble space telescope
November 22, 2024 at 9:09 AM
💯 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
Reposted by Maria Gorinova
I got a Probabilistic Programming starter pack going. Hit me up if you're involved with #probprog R&D and want in!
go.bsky.app/JfvubEf
go.bsky.app/JfvubEf
November 19, 2024 at 4:10 PM
I got a Probabilistic Programming starter pack going. Hit me up if you're involved with #probprog R&D and want in!
go.bsky.app/JfvubEf
go.bsky.app/JfvubEf
Reposted by Maria Gorinova
Bluesky tip for newbies: Bluesky has no real algorithm. Likes here do nothing but show the poster that you enjoyed their content.
That kindness is always going to be appreciated by creators, but if you want to help to boost something here, you have to repost it so others see it. 🙂
That kindness is always going to be appreciated by creators, but if you want to help to boost something here, you have to repost it so others see it. 🙂
November 18, 2024 at 10:27 AM
Bluesky tip for newbies: Bluesky has no real algorithm. Likes here do nothing but show the poster that you enjoyed their content.
That kindness is always going to be appreciated by creators, but if you want to help to boost something here, you have to repost it so others see it. 🙂
That kindness is always going to be appreciated by creators, but if you want to help to boost something here, you have to repost it so others see it. 🙂
Reposted by Maria Gorinova
Yet another plea to people who are using or following people off follow-farming hashtags like #NoDemUnder1K, #NoDemUnder5K, #BlueCrew, #FBR, etc etc: please do not do that, it's how disinformation operations work. I'm already seeing accounts in those hashtags that are likely disinformation ops. 1/
November 15, 2024 at 2:28 PM
Yet another plea to people who are using or following people off follow-farming hashtags like #NoDemUnder1K, #NoDemUnder5K, #BlueCrew, #FBR, etc etc: please do not do that, it's how disinformation operations work. I'm already seeing accounts in those hashtags that are likely disinformation ops. 1/
Reposted by Maria Gorinova
Reposted by Maria Gorinova
November 18, 2024 at 1:53 PM
Reposted by Maria Gorinova
I made a starter pack for Bayesian ML and stats (mostly to see how this starter pack business works).
Let me know whom I missed!
go.bsky.app/2Bqtn6T
Let me know whom I missed!
go.bsky.app/2Bqtn6T
November 18, 2024 at 4:19 PM
I made a starter pack for Bayesian ML and stats (mostly to see how this starter pack business works).
Let me know whom I missed!
go.bsky.app/2Bqtn6T
Let me know whom I missed!
go.bsky.app/2Bqtn6T
OMG my feed here is so delightful. A beautiful mix of ML, nerdy jokes, and some high-quality journalism. I've missed this so much 🥲 ✨ 🦋
November 18, 2024 at 6:52 PM
OMG my feed here is so delightful. A beautiful mix of ML, nerdy jokes, and some high-quality journalism. I've missed this so much 🥲 ✨ 🦋
How do people work out what instance they need on AWS? There are so many options I get choice paralysis
November 18, 2024 at 1:16 PM
How do people work out what instance they need on AWS? There are so many options I get choice paralysis
Reposted by Maria Gorinova
I made a starter pack for researchers in probabilistic machine learning.
DM/reply if you want to be added!
go.bsky.app/DuCtJqC
DM/reply if you want to be added!
go.bsky.app/DuCtJqC
November 18, 2024 at 2:00 AM
I made a starter pack for researchers in probabilistic machine learning.
DM/reply if you want to be added!
go.bsky.app/DuCtJqC
DM/reply if you want to be added!
go.bsky.app/DuCtJqC