Sign in

Maria Gorinova

@mgorinova.bsky.social
2.2K followers 443 following 141 posts

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. mgorinova.github.io

PostsRepliesMedia
Maria Gorinova @mgorinova.bsky.social · 17/08/2026
Aaaand, it's out! Check out the full documentary here: youtu.be/u37qkpp5eB8?... 🍿
youtu.be
Inside Kikimora: We Built a Dark Software Factory
YouTube video by AI Native Dev
010
Maria Gorinova @mgorinova.bsky.social · 12/08/2026
Never thought I'd be a part of an intense netflix-style documentary, but here we go 😅 Want to learn more about the #softwarefactory and how we built one that the whole @tessl.io team is using? Stay tuned for the full video!
241
Maria Gorinova @mgorinova.bsky.social · 08/08/2026
Want to catch them at #KDD2026 tomorrow? 🛠 Coding benchmarks are misaligned with #AgenticSE → Agentic Software Engineering (SE 3.0) agent-se.github.io 🧪 #AgenticSkills evals at scale → Evaluation & Trustworthiness of Agentic AI kdd-eval-workshop.github.io/agenticai-ev... Come chat to us!
010
Maria Gorinova @mgorinova.bsky.social · 08/08/2026
2/ A Framework for Evaluating Agentic Skills at Scale We evaluate 500 real-world skills, 1,000 tasks & 19 agent-model configurations, asking when skills actually make agents better. You can already use our evals as part of @tessl.io's offering! arxiv.org/abs/2606.17819 #AgenticAI #AIEvaluation
arxiv.org
A Framework for Evaluating Agentic Skills at Scale
Agent skills -- structured, reusable knowledge artifacts that augment LLM agent capabilities -- have been rapidly adopted in industry, yet their cross-domain impact and use across commercial and open-...
131
Maria Gorinova @mgorinova.bsky.social · 08/08/2026
1/ Coding Benchmarks Are Misaligned with Agentic Software Engineering On #CodingAgents, #HarnessEngineering & #SoftwareFactory and why today's coding benchmarks are not designed to adequately evaluate coding ability of such increasingly complex systems. arxiv.org/abs/2606.17799
arxiv.org
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and environment into a single ...
241
Maria Gorinova @mgorinova.bsky.social · 08/08/2026
🎉 So excited to share we are presenting two @tessl.io AI Research papers at #KDD2026 workshops in Jeju on Sunday! Both papers ask: how do we meaningfully evaluate increasingly complex agentic AI systems and the components around them? Rob Willoughby will be presenting both — come say hi! 🇰🇷 🧵👇
151
Maria Gorinova @mgorinova.bsky.social · 16/12/2025
Learn more about our work on abstraction adherence of coding agents! www.youtube.com/watch?v=nx5_... #coding #aicoding #agenticai #codegen #devtools #cursor #claudecode
youtube.com
The Population Test Your Agent Must Pass | Maria Gorinova
YouTube video by AI Native Dev
030
Maria Gorinova @mgorinova.bsky.social · 09/12/2025
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
010
Reposted by Maria Gorinova
Simon Willison @simonwillison.net · 27/11/2025
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
8877274
Reposted by Maria Gorinova
AI Native Dev @ainativedev.io · 26/11/2025
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...
luma.com
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…
163
Maria Gorinova @mgorinova.bsky.social · 20/11/2025
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...
tessl.io
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.
050
Maria Gorinova @mgorinova.bsky.social · 26/09/2025
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.
040
Maria Gorinova @mgorinova.bsky.social · 10/08/2025
"I really need a tool that helps me count the number of letters in 'blueberry'. It will change my life." ... said no one ever.
media.tenor.com
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"
020
Maria Gorinova @mgorinova.bsky.social · 03/08/2025
media.tenor.com
a pirate hat with a skull and crossbones and a sword on it
Alt: a cat with a pirate hat with a skull and crossbones and a sword on it
010
Maria Gorinova @mgorinova.bsky.social · 03/08/2025
I stole this for the linkedin post 😂 Gratitude 🫡
110
Maria Gorinova @mgorinova.bsky.social · 03/08/2025
Aaaaaaa! I'm regretting my choices 🥲
020
Maria Gorinova @mgorinova.bsky.social · 03/08/2025
I actually like the em dash. Am I an LLM? 🤔
2180
Maria Gorinova @mgorinova.bsky.social · 26/05/2025
A few years late but I was finally able to generate this
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"
060
Maria Gorinova @mgorinova.bsky.social · 11/02/2025
What I imagine open ai feels like after reading that s1 paper
media.tenor.com
a man is holding a piece of bread over a woman 's face and asking what are you ?
ALT: a man is holding a piece of bread over a woman 's face and asking what are you ?
020
Maria Gorinova @mgorinova.bsky.social · 11/02/2025
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
120
Reposted by Maria Gorinova
Hunter Walker @hunterw.bsky.social · 26/11/2024
🚨 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...
bsky.app
2412758630
Maria Gorinova @mgorinova.bsky.social · 25/11/2024
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!
020
Maria Gorinova @mgorinova.bsky.social · 25/11/2024
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
220
Maria Gorinova @mgorinova.bsky.social · 25/11/2024
I love Silo and For All Mankind. Maybe I should try Halt & Catch Fire next!
110
Maria Gorinova @mgorinova.bsky.social · 24/11/2024
Thank you! Indeed, what a debacle 😂 🍿
010
Maria Gorinova @mgorinova.bsky.social · 23/11/2024
What's the drama with Byzantine? Did someone raise it during reviewing in the past? Is there a public discussion? 🍿
110
Reposted by Maria Gorinova
Jay 🦋 @jay.bsky.team · 23/11/2024
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
docs.bsky.app
Bluesky Documentation | Bluesky
Explore guides and tutorials to the Bluesky API.
31878431517
Reposted by Maria Gorinova
Christoph Molnar @christophmolnar.bsky.social · 22/11/2024
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...
Book outlineOver 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
22647101
Maria Gorinova @mgorinova.bsky.social · 22/11/2024
💯 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
140
Maria Gorinova @mgorinova.bsky.social · 22/11/2024
Personally, I like Quiet Posters: it surfaces posts I wouldn't have seen otherwise!
000
Maria Gorinova @mgorinova.bsky.social · 20/11/2024
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 (💅🏻))
111
Maria Gorinova @mgorinova.bsky.social · 20/11/2024
Maybe we need a special sarcasm tag here on bsky
110
Maria Gorinova @mgorinova.bsky.social · 20/11/2024
My question was a joke! I know what the word means 🤣
220
Maria Gorinova @mgorinova.bsky.social · 20/11/2024
What do you mean "once"? 🤨
110
Reposted by Maria Gorinova
Chad Scherrer @cscherrer.bsky.social · 19/11/2024
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
2211630
Maria Gorinova @mgorinova.bsky.social · 19/11/2024
Thanks, Chad! Much needed starter pack 🙌🏻
010
Reposted by Maria Gorinova
Tim Baxter @timinclimate.naruresearch.com.au · 18/11/2024
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. 🙂
20261609104
Reposted by Maria Gorinova
rahaeli @rahaeli.bsky.social · 15/11/2024
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/
17040881979
Reposted by Maria Gorinova
Kara Swisher @karaswisher.bsky.social · 18/11/2024
Hey kids we brought @pivotpod.bsky.social over too. bsky.app/profile/pivo...
bsky.app
83103788
Reposted by Maria Gorinova
Rami Krispin @ramikrispin.bsky.social · 18/11/2024
A growth rate of ~10 users per second 🤯 Great dashboard by @natalie.sh! bcounter.nat.vg
1303
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
Ahahha this is so accurate! Being Eastern European, I guess my response is meh
media.tenor.com
a man in a black jacket is making a funny face and saying `` meh ! ''
ALT: a man in a black jacket is making a funny face and saying `` meh ! ''
000
Reposted by Maria Gorinova
Vincent Fortuin @vincefort.eurosky.social · 18/11/2024
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
529333
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
I do that as a first step. But AWS is so confusing, the requirements are not straightforward. I still don't know if what I'm trying will work 🤷🏻‍♀️
020
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
Literally what I did 🙌 Turned out running the job on the expensive instance is cheaper than running it on the cheap instances because it will finish quicker 😱
000
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
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 🥲 ✨ 🦋
0120
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
How do people work out what instance they need on AWS? There are so many options I get choice paralysis
210
Maria Gorinova @mgorinova.bsky.social · 18/11/2024
Honoured to be on here, thank you! 🙌
000
Reposted by Maria Gorinova
Tim G. J. Rudner @timrudner.bsky.social · 17/11/2024
I made a starter pack for researchers in probabilistic machine learning. DM/reply if you want to be added! go.bsky.app/DuCtJqC
6610536