mrdrozdov Profile Banner
Andrew Drozdov Profile
Andrew Drozdov

@mrdrozdov

Followers
3K
Following
13K
Media
615
Statuses
13K

Context Engineering (and Science!) for Knowledge Assistant @ Databricks

NYC
Joined August 2010
Don't wanna be here? Send us removal request.
@mrdrozdov
Andrew Drozdov
23 days
Tweet media one
0
2
13
@mrdrozdov
Andrew Drozdov
7 hours
RT @HanSineng: Missing @aclmeeting but sending “ATEB: Rethinking Advanced NLP Tasks in an Information Retrieval Setting” in my place ! . Co….
0
4
0
@mrdrozdov
Andrew Drozdov
18 hours
RT @beirmug: TREC RAG 2025 official retrieval baselines are available now! 💥💥💥 . Time to start generating those answers and submit them to….
0
3
0
@mrdrozdov
Andrew Drozdov
2 days
RT @TacoCohen: What I look for when hiring? EXTREME PARANOIA about code and data.
0
12
0
@mrdrozdov
Andrew Drozdov
2 days
This aligns with #2 in the proposals I described at the #SIGIR2025 panel on “LLMs and IR”. Really cool to see a whole team forming to tackle this effort!.
@Jack_W_Lindsey
Jack Lindsey
3 days
We're launching an "AI psychiatry" team as part of interpretability efforts at Anthropic!  We'll be researching phenomena like model personas, motivations, and situational awareness, and how they lead to spooky/unhinged behaviors. We're hiring - join us!
0
0
1
@mrdrozdov
Andrew Drozdov
2 days
RT @ao_qu18465: 🚀 Excited to share my first tweet and to introduce our latest work: MEM1: RL for Memory Consolidation in Long-Horizon Agent….
0
10
0
@mrdrozdov
Andrew Drozdov
3 days
RT @VoyageAI: 📢 voyage-context-3: contextualized chunk embeddings. - Auto captures of chunk level detail & global doc context, w/o metadata….
0
22
0
@mrdrozdov
Andrew Drozdov
3 days
RT @ziv_ravid: We want to start a podcast about cutting-edge AI research and technical breakthroughs. Need a catchy name!.What would you ca….
0
7
0
@mrdrozdov
Andrew Drozdov
4 days
RT @MohitIyyer: ChatGPT Agent is a huge step up on BearCubs, esp on multimodal/interactive tasks (e.g., playing web games)!. It gets 65.8%….
0
4
0
@mrdrozdov
Andrew Drozdov
5 days
RT @wzhao_nlp: Silly but important question: what metrics do you look at / how to vibe-check your training runs are going well, specially u….
0
9
0
@mrdrozdov
Andrew Drozdov
5 days
RT @kchonyc: 😂 @wellecks , i think this “challenging problem” may have been finally solved after five years. ===.Understanding and creatin….
0
8
0
@mrdrozdov
Andrew Drozdov
5 days
RT @lateinteraction: Haha. Well, if you want to read @SherylHsu02’s excellent last paper just before joining OpenAI, read LeReT at ICLR’25.….
0
25
0
@mrdrozdov
Andrew Drozdov
5 days
RT @random_walker: Back in grad school, when I realized how the “marketplace of ideas” actually works, it felt like I’d found the cheat cod….
0
51
0
@mrdrozdov
Andrew Drozdov
6 days
RT @mrdrozdov: Here's three of my more *controversial* proposals from the SIGIR / ICTIR 2025 panel on "LLMs + IR, what could possibly go wr….
0
2
0
@mrdrozdov
Andrew Drozdov
6 days
A cool outcome here would be if future IMO exclusively includes problems that we know recent generation of LLMs can not yet solve.
@ErnestRyu
Ernest Ryu
7 days
6. I don’t think LLMs will replace mathematicians anytime soon. Math research is about solving problems *no one* yet knows how to solve (out-of-distribution), and this requires significant creativity, something notably absent from OpenAI’s IMO solutions. (6/10).
2
0
3
@mrdrozdov
Andrew Drozdov
6 days
I’m interpreting this as pro-Human rather than anti-AI. Give people time and tools, and be amazed.
@pli_cachete
Rota
7 days
Terence Tao on the supposed Gold from OpenAI at IMO
Tweet media one
Tweet media two
Tweet media three
0
0
1
@mrdrozdov
Andrew Drozdov
7 days
RT @lateinteraction: AegisLLM leverages DSPy's MIPROv2 optimizer in a totally unexpected way: to evolve its prompts based on the attacks it….
0
17
0
@mrdrozdov
Andrew Drozdov
7 days
“Reasoning won’t generalize outside of math and code”. Maybe we should express everything as math and code…. Proofs, Theorems, Lemmas, Corollaries, Conjectures are all math. It’s not just equations. From this perspective we have a lot more flexibility of expression.
1
0
2
@mrdrozdov
Andrew Drozdov
7 days
RT @MohitIyyer: Excited to talk about long-context models / eval at this panel on Saturday! I'm also looking for a postdoc / PhD students t….
0
11
0