Co-founder DrivenData. Celebrating a decade of data for good. ML challenges | https://www.drivendata.org/ Data projects | https://drivendata.co/ Open source | https://github.com/pjbullhttps://bsky.app/profile/peter.drivendata.orghttps://bsky.app/profile/peter.drivendata.org/post/3mqcg4qbs2c2bCheck out this challenge to understand real tutoring transcripts! [contains quote post or other embedded content]10 Jul 2026 15:01 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3mqcg4qbs2c2bhttps://bsky.app/profile/peter.drivendata.org/post/3mp2xjxrvsu2eFirst benchmark shared on K-12 AI Infrastructure Platform! Frontier models* don't outperform classical methods on grading science short answer questions. https://platform.k12-ai-infrastructure.org/benchmarks/2/sage-benchmark/leaderboard/ (zero-short, few-shot, reasoning off).24 Jun 2026 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3mp2xjxrvsu2ehttps://bsky.app/profile/peter.drivendata.org/post/3mogmf6lmdz2rLaunching today: The K-12 AI Infrastructure Platform! platform.k12-ai-infrastructure.org Making AI better for students and educators. Learn more about the launch and our plans on the blog post here: https://drivendata.co/blog/k12-ai-infrastructure-platform-launch16 Jun 2026 20:14 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3mogmf6lmdz2rhttps://bsky.app/profile/peter.drivendata.org/post/3migyjxfp352qExcited to be speaking at Good Tech Summit in DC April 7 www.goodtechtogether.org/summit We’ll share a program focused on K-12 education and talk about investing in the foundations of AI: data, models, and benchmarks. We'll explore how these shape AI development in a field. Join us!01 Apr 2026 15:20 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3migyjxfp352qhttps://bsky.app/profile/peter.drivendata.org/post/3me33dw6akm2c🎉 Excited to launch this challenge! 🎉 Over a year of data collection, curation, and annotation that we undertook to produce a first-of-its-kind dataset. Help us build speech models that understand 2-5 year olds. $120k in prizes and huge impact! kidsasr.drivendata.org04 Feb 2026 23:58 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3me33dw6akm2chttps://bsky.app/profile/peter.drivendata.org/post/3m47fnefglp2oGreat set of events for #SeattleAIWeek this week! Definitely join some if you are in town and let me know if you want to catch up https://luma.com/Seattle-AI-Week-202527 Oct 2025 21:51 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3m47fnefglp2ohttps://bsky.app/profile/peter.drivendata.org/post/3m33u73o45d2e🚀 New release: cloudpathlib v0.23.0 🥧 Now with Python 3.14 (π) support! 📁 New copy & move methods mean you can reduce usage of shutil 🎉 Check out the full release and docs here: 👉 cloudpathlib.drivendata.org/stable/13 Oct 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3m33u73o45d2ehttps://bsky.app/profile/peter.drivendata.org/post/3m2ucsd3dja2mSuper interesting work on new proposed columnar data file format called F3 with embedded wasm binary to decode the data 🤯 (which obviates the need for 3rd party library support). Favorable comparisons on compression, throughput and random reads to existing formats. https://db.cs.cmu.edu/papers/2025/zeng-sigmod2025.pdf10 Oct 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3m2ucsd3dja2mhttps://bsky.app/profile/peter.drivendata.org/post/3m2porke33t2eVery cool to see Wikimedia embracing LLM tools and launching a hybrid similarity search API and open source embeddings for Wikipedia! Also supports Q&A style queries. https://www.wikidata.org/wiki/Wikidata:Embedding_Project08 Oct 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3m2porke33t2ehttps://bsky.app/profile/peter.drivendata.org/post/3m2kawn3bcx2mInteresting to see empirical research coming out for LLMs as education aids. In this study, active use of LLMs helped CS students debug compiler errors. Removing LLM access demonstrated no lasting learning benefit from having had access to it... https://learninganalytics.upenn.edu/ryanbaker/ICCE2025_paper_28.pdf06 Oct 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3m2kawn3bcx2mhttps://bsky.app/profile/peter.drivendata.org/post/3lzh2frja5j2pWe just shipped two major features for cloudpathlib ✨📦 ✨ ! First, http support—treat an URL like any other path (open, read_text, join). Second, compatibility with open and os Python built-ins for seamless transition of legacy code and third-party library support. cloudpathlib.drivendata.org22 Sep 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lzh2frja5j2phttps://bsky.app/profile/peter.drivendata.org/post/3lz7iyy6qju25Great opportunity to work on AI in conservation and biodiversity with Roland Kays! In-person in NC, check it out now since it is only open for a week: https://www.governmentjobs.com/careers/%7B0%7Dnorthcarolina/jobs/newprint/502123919 Sep 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lz7iyy6qju25https://bsky.app/profile/peter.drivendata.org/post/3lwuhwfya2j2cExemplary FAQ for "Your Brain on ChatGPT: Accumulation of Cognitive Debt" www.brainonllm.com/faq I'd love to see more authors who are explicit about what NOT to claim based on a study, including wording for lay audiences that is not appropriate. https://www.brainonllm.com/faq20 Aug 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lwuhwfya2j2chttps://bsky.app/profile/peter.drivendata.org/post/3lwcunxomrz2qThought I would spot check a application someone was posting about 100% vibecoding. Can you spot the issue? Kudos to the LLM, this is verbatim from the fastapi docs. Sometimes verbatim from the docs is not what you want for your application though....13 Aug 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lwcunxomrz2qhttps://bsky.app/profile/peter.drivendata.org/post/3lwcizjymkc2nInteresting announcement on a product from Astral! Similar model to one of the core @anacondainc.bsky.social lines of business. [contains quote post or other embedded content]13 Aug 2025 18:58 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lwcizjymkc2nhttps://bsky.app/profile/peter.drivendata.org/post/3lvvvgchzpo2kEnthusiastic to build on this generation of earth observation foundation embeddings like DeepMind's AlphaEarth (and more)! We already see some promising crop type (cereals vs. orchards) results and are exploring other use cases in climate resilience. https://deepmind.google/discover/blog/alphaearth-foundations-helps-map-our-planet-in-unprecedented-detail/08 Aug 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lvvvgchzpo2khttps://bsky.app/profile/peter.drivendata.org/post/3lvec5xipze2kVery cool to see that marimo supports our cloudpathlib library for their file browser UI! Browse your S3, GCS, Azure buckets from your notebooks! https://docs.marimo.io/api/inputs/file_browser/01 Aug 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lvec5xipze2khttps://bsky.app/profile/peter.drivendata.org/post/3lusovj25r32w✨ 📦 ✨ Just released new Cookiecutter Data Science version with support for pixi and poetry as environment managers! Some of our top requested features ever. Upgrade and check it out now. cookiecutter-data-science.drivendata.org25 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lusovj25r32whttps://bsky.app/profile/peter.drivendata.org/post/3lub3nngdwc2jNow getting organic inbound for www.zambacloud.com, our wildlife imagery processing platform, from ChatGPT! 😲18 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lub3nngdwc2jhttps://bsky.app/profile/peter.drivendata.org/post/3lu4hmrow3k2zJust in case you thought speech-to-text worked for children, the third column is what Whisper does. Somehow in the third example it accesses my inner monologue... I guess that's why we're excited about our upcoming challenge! kidsasr.drivendata.org16 Jul 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lu4hmrow3k2zhttps://bsky.app/profile/peter.drivendata.org/post/3ltwzrmncxt2zHow are people managing code review for their AI coding agents? I do a first glance and it is obviously bad (e.g., didn't refactor repeated code), and now I've got half a dozen AI diffs for things that aren't good enough cluttering up my todo list with things to respond to....14 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3ltwzrmncxt2zhttps://bsky.app/profile/peter.drivendata.org/post/3ltpieqtl7j24New research based on the CANDOR corpus shows that people enjoy conversations where they alternate longer turns better than short turns or one person dominating. Cool! https://arxiv.org/html/2506.20474v211 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3ltpieqtl7j24https://bsky.app/profile/peter.drivendata.org/post/3ltkue4eaka26The best shortcut to how many experienced software engineers feel about AI is listening to the Primeagen's takes. Balanced perspectives on what's actually new, determinism, security, system complexity, what's promising, and what's not https://www.youtube.com/watch?v=vDWaKVmqznQ09 Jul 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3ltkue4eaka26https://bsky.app/profile/peter.drivendata.org/post/3ltfgj7ltso2p"Damn ChatGPT" your new summer jam about using ChatGPT as a therapist https://open.spotify.com/track/4umq06kfyvtQMlBALXhxuI?si=28e550e13b3f488f (edited)07 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3ltfgj7ltso2phttps://bsky.app/profile/peter.drivendata.org/post/3lt5v4eicqg2aGreat article on the challenges of only surfacing the right info to LLMs and editing down what is not needed. If you've used a coding copilot or agent, you've seen this first hand many times. Output iterations are often polluted with code that came before. https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-how-to-fix-them.html04 Jul 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lt5v4eicqg2ahttps://bsky.app/profile/peter.drivendata.org/post/3lsttawmsvh2pBioCLIP2 looks like a stellar improvement! I'm excited to think about integrating into Zamba to for open-ended classification tasks run at scale on camera trap imagery. Definitely the potential to dramatically improve CT image utility. imageomics.github.io/bioclip-2/30 Jun 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lsttawmsvh2phttps://bsky.app/profile/peter.drivendata.org/post/3lsmbu23d5w2k"Munchable" is GenZ cringe. https://www.propublica.org/article/inside-ai-tool-doge-veterans-affairs-contracts-sahil-lavingia https://www.propublica.org/article/inside-ai-tool-doge-veterans-affairs-contracts-sahil-lavingia?utm_source=twitter&utm_medium=social&utm_campaign=propublica-twitter&utm_content=thread27 Jun 2025 18:36 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lsmbu23d5w2khttps://bsky.app/profile/peter.drivendata.org/post/3lshntdx5kc2kWe've built so many low-fidelity prototypes in our HCD work. IMO vibecoding changes the feel of those prototypes, but doesn't change the process. Ask any designer—they'll tell you high-fidelity first iterations are often more distracting to clients than helpful. https://www.semafor.com/article/06/05/2025/the-ease-of-vibe-coding-could-upend-the-economics-of-scarcity-and-scale25 Jun 2025 22:27 +0000at://did:plc:cj3tyjxjickqinscsrn2hwfd/app.bsky.feed.post/3lshntdx5kc2k