Claire Longo (@StatInStilettos) header
Claire Longo (@StatInStilettos) profile picture

Claire Longo

@StatInStilettos

Poker. Mathematics. AI.

 Digital Nomad
linktr.ee/statisticianinstilettos
Joined March 2016
  • Tweets123
  • Following159
  • Followers102
12Media
Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)Photo by Claire Longo (@StatInStilettos)
Where in the world is Claire? 🌵 ☀️ Working for a remote first tech company is amazing! Last week I was in Scottsdale and Sedona Arizona spending quality time with family, and working away on my latest research project on LLM evals. #remotejob #womeninscience (We're hiring!)
Image from Claire Longo (@StatInStilettos)
Image from Claire Longo (@StatInStilettos)
Image from Claire Longo (@StatInStilettos)
2
4
570
Claire Longo retweeted
Vincent Koc (@vincent_koc) profile picture
Vincent Koc
@vincent_kocJan 9
It's 2026 and we @Cometml decided to reward the community on working on some projects for themselves. We have a $30k USD cash prize pool for our three week virtual online hackathon. Spaces are filling up, get on the Tuesday kick off. luma.com/commit_to_change_ha…
Global AI Agents Hackathon $30k Cash Prizes · Luma

Global AI Agents Hackathon $30k Cash Prizes · Luma

🎉 Join us as we kick off a Global AI Agents Hackathon with $30K in cash prizes on the line. The Challenge Build an AI agent that actually helps people follow…

luma.com
8
35
1
52
4,881
Claire Longo retweeted
Ali Sufian (@aliscodes) profile picture
Ali Sufian
@aliscodes16 Dec 2025
AI agents fail for one quiet reason. Their prompts never improve. You write a prompt once, ship it, and hope it works. When it breaks, you manually tweak it again. This does not scale. And it is about to get worse. 👇
Image from Ali Sufian (@aliscodes)
25
13
1
39
10,080
This girl literally explained LLMOps better than most talks, in under 7 minutes.
7
36
1
279
18,881
Replying to @gidim
I recently posted about this: teapawt.net/akshay_pachaar/status/… Great to see someone doing the work that actually matters!
Akshay 🚀 (@akshay_pachaar) profile pictureAkshay 🚀
@akshay_pachaar26 Aug 2025
I boosted my AI Agent's performance by 184% Using a fully open-source, automatic technique Here's a breakdown (with code):
1
2
3,016
Claire Longo retweeted
Gideon M (@gidim) profile picture
Gideon M
@gidim15 Dec 2025
Switching to GPT-5.2 won’t fix your broken agent. Neither will switching to Gemini 3, Claude 4.5, or Kimi-V100.72-Deep-Thinking-Pro-Flash-Nano. And the reason is simple: You don’t need OpenAI to train a better model. You need to train a better agent. 🧵
19
26
15
80
78,815
Claire Longo retweeted
Vincent Koc (@vincent_koc) profile picture
Vincent Koc
@vincent_koc18 Nov 2025
Living in 2025 with - My @Spotify AI DJ hitting me with vibe evening tunes from @odesza - Got 4 tabs of @OpenAI codex running in my tmux window on another screen - @Grubhub keeping me fed from the local food spot Totally locked in ;) - Photo is from one my favourite trails along SF
Image from Vincent Koc (@vincent_koc)
1
2
443
⭐⭐⭐New speakers announced for the 6th Annual @MLOpsWorld Summit (Oct 8-9, Austin). New sessions added from @pagerduty, @BlackRock, @Cometml, @patternhq, & @usebraintrust tackle testing, evals, and scaling. Early Bird ends Sept 8, 11:59PM ET → mlopsworld.com/speakers/?utm…
Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

ALT Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

ALT Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

ALT Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

ALT Early Bird pricing ends Monday, Sept 8 at 11:59PM ET. Visit: mlopsworld.com The latest wave of speakers for the 6th annual MLOps World | GenAI Summit 2025 (Oct 8–9, Austin Renaissance Hotel) brings lessons from PagerDuty, BlackRock, Comet, Pattern AI, and Braintrust. Every session has been curated by volunteer AI practitioners whose only goal is to deliver real-world value you can apply immediately to make your AI systems more reliable, scalable, and production-ready. Active learning continues beyond the sessions with engagement at our Expo, featuring Brain Dates, Community Square, the Startup Zone, and interactive demos. Speakers representing leading technologists from Microsoft, OpenAI, BestBuy, PayPal, Shopify, and Yahoo will be announced shortly.

2
4
261
I am hosting Las Vegas Hack Night. Join me! lu.ma/hack-night-las-vegas-8… via @LumaHQ

Las Vegas AI Hack Night · Luma

Join us for Hack Night in Las Vegas! AI-assisted coding has been all the rage, and many expert developers are figuring out creative ways to leverage AI to…

luma.com
165
Claire Longo retweeted
Vincent Koc (@vincent_koc) profile picture
Vincent Koc
@vincent_koc11 Jun 2025
In Paris 🇫🇷 for #GTCParis and #VivaTech2025 and this place is an endless sea of AI companies, tech infrastructure and everything in between.
Image from Vincent Koc (@vincent_koc)
Image from Vincent Koc (@vincent_koc)
Image from Vincent Koc (@vincent_koc)
Image from Vincent Koc (@vincent_koc)
2
12
63
76,655
Claire Longo retweeted
Santiago (@svpino) profile picture
Santiago
@svpino3 Jun 2025
Build your first AI agent + MCP Server in Python. Here is everything you need to build your first AI agent in less than 20 minutes. About the code you'll see here: 1. I used Google ADK with Gemini Flash to power the agent 2. The agent connects to an MCP server 3. It also uses two custom tools to do its work 4. You can see everything the agent does thanks to @Cometml's Opik library Here is the video, free for you to watch.
27
160
6
917
56,729
Claire Longo retweeted
Qdrant (@qdrant_engine) profile picture
Qdrant
@qdrant_engine31 May 2025
Advanced Hybrid RAG with miniCOIL, LangGraph, and @deepseek_ai 🚀 @TRJ_0751 shows how to build a hybrid Customer Support RAG chatbot using miniCOIL to augment sparse retrieval with semantic awareness ➡️ LangGraph by @langchain orchestrates the hybrid flow with MMR and re-ranking ➡️ Opik tracks and evaluates each step of the pipeline ➡️ DeepSeek-R1 by @SambaNovaAI delivers low-latency, focused answers 👉 Read it here: medium.aiplanet.com/advanced…
Image from Qdrant (@qdrant_engine)
1
25
3
149
10,717
I've been thinking a lot about Agent evals... while LLM as a Judge works great for text, how are y'all approaching evaluation metrics for voice, image and/or video? 🤔
154
Claire Longo retweeted
Comet (@Cometml) profile picture
Comet
@Cometml30 Apr 2025
That’s a wrap on #AWSSummit London! 🚀 Next stop: Amsterdam 🇳🇱 for an @AITinkerers on May 6th. Still time to snag a spot 👉 amsterdam.aitinkerers.org/p/…
Image from Comet (@Cometml)
Image from Comet (@Cometml)
1
3
5
837
⭐️⭐️ Lecture 9 of @MITDeepLearning 2025 is now available online #FREE for ALL! Should there be a Hippocratic Oath for #AI? Tune in to hear about this from the amazing @DougBlank3 of @Cometml! 🚀 🔥 Lecture 👉 youtube.com/watch?v=CyCUZAf8… 🌐 Website 👉 IntroToDeepLearning.com
Image from MIT Intro to Deep Learning (@MITDeepLearning)
8
18
1,979
Reinforcement Learning (RL) is quickly becoming the most important skill for AI researchers. Here are the best resources for learning RL for LLMs… TL;DR: RL is more important now than it has ever been, but (probably due to its complexity) there aren’t a ton of great resources for learning it online. I’ve been doing a lot of reading / learning on RL recently, so I wanted to share the best resources I’ve found. Links to all resources are provided in the image below. (1) RLHF book. Nathan is a long-time RL researcher and an expert on LLM alignment / post-training. He decided to write an entire book on (LLM-focused) RL techniques and has been slowly expanding / iterating on the book over the last year. This is the most comprehensive RL resource that is currently available, and it’s an especially great resource for those who are unfamiliar with RL and still need to learn the basics. (2) The Spinning up with Deep RL Course from OpenAI–despite being created in ~2018–has stood the test of time and is one of the best tutorials for learning RL. This course builds up to understanding PPO, which is one of the most widely used algorithms for RL with LLMs. Plus, understanding related algorithms (policy gradients, TRPO, etc.) will help a lot with gaining an understanding of new RL algorithms like GRPO. (3) PPO / GRPO blog. Jimmy Shi (DeepMind) recently wrote a great blog explaining both PPO (RL algo traditionally used for RLHF) and GRPO (RL algo used for reasoning models). This blog is great and it’s written in a way that is understandable for non-RL people. (4) HuggingFace RL. HuggingFace has also published numerous useful blogs on the topic of RL. Most recently, they published a blog that explains GRPO and PPO from the ground up (i.e., not assuming any background knowledge on RL). These blogs are inspired by the recent initiative from HuggingFace to create a fully open replication of DeepSeek-R1.
Image from Cameron R. Wolfe, Ph.D. (@cwolferesearch)
23
277
13
1,280
114,524
👨‍💻 How do we improve AI Agent transparency and reliability? @StatInStilettos will dive into AI Agent observability, sharing how logging traces and monitoring help track Agent behavior and detect failures! 👉 April 15, 2025 | Register here: bit.ly/AgentsandGenAI
Image from MLOps World | GenAI Summit (@MLOpsWorld)
2
1
198
6 years ago, I decided to open-source my Python code for a personal project I was working on, which led to numerous career successes that followed. Not just for myself but for some of the folks I met and collaborated with. Anyone else have a similar experience?
2
104
Now, I'm working with Opik, Comet's open-source library for LLM Observability. If you want to build your resume by contributing to OSS, I can help you! Opik is a great place to start. on the issues page, you will find some low-hanging fruit. github.com/comet-ml/opik/iss…
Issues · comet-ml/opik

Issues · comet-ml/opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. - Issues · comet-ml/opik

github.com
154
Creating and contributing to open-source projects helped me; 🔷 Build a developer portfolio to showcase my code 🔷 Be prepared for coding interviews 🔷 Connect with people who served as professional references
86
Let's compare Llama 4 and DeepSeek-R1 using RAG:
22
115
10
1,122
358,315
Load more