John Trengrove

Applied Research @weaviate_io

[vicki @vboykis]

search is absolutely unusable now to surface old tweets so just going to repost: there are two fundamental problems in computing, (ironically) search and compression

[John Trengrove @trengrj]

@CJHandmer This seems needlessly alarmist when Australia spends roughly half the US on healthcare per capita and robotics in aged care will be transformative.

[John Trengrove @trengrj]

@lateinteraction https://t.co/Lf113DSWIg

[John Trengrove @trengrj]

Great LIR keynote by @lateinteraction and 100% this on the need for less vectors per token in these models.

[John Trengrove @trengrj]

@lateinteraction As an example look at this table on storage efficiency from Nemotron ColEmbed V2. The single vector model uses nearly 1000x less storage. Compression of residuals etc means the factor is less in practice but there is so much efficiency left on the table.

[John Trengrove @trengrj]

Wow apparently Google benchmarked a single-core CPU for RaBitQ vs an A100 GPU for TurboQuant

[Jianyang Gao @gaoj0017]

We need to publicly clarify serious issues in Google’s ICLR 2026 paper TurboQuant.

TurboQuant misrepresents RaBitQ in three ways:
1. Avoids acknowledging key methodological similarity (JL transform)
2. Calls our theory “suboptimal” with no evidence
3. Reports results under unfair experimental settings

We have expressed our concerns to the authors before their submission, but they chose not to fix them in their paper submission. The paper was accepted at ICLR 2026 and heavily promoted by Google (tens of millions of views). At that scale, uncorrected claims quickly become “consensus.”

Facts:
1. RaBitQ already proves asymptotic optimality (FOCS’17 bound)
2. TurboQuant uses the same random rotation step but misses stating the connection
3. Their experiments used single-core CPU for RaBitQ vs A100 GPU for TurboQuant

None of these is properly disclosed.

We’ve filed a formal complaint and posted on OpenReview (https://t.co/nDVjmNhATM).
We’ll release a detailed technical report on arXiv.

Our goal is simple: keep the academic record accurate.

Would appreciate people taking a look and sharing.

[John Trengrove @trengrj]

@andersonbcdefg Haha they should sell a recursive stack of crawling and anti-crawling services with continually increasing prices.

[John Trengrove @trengrj]

Hey @bclavie, we primarily were showing memory reduction (80%+) and QPS improvements with the set of MUVERA parameters in the blog post. I agree sometimes you would want to increase projections for less memory reduction and higher recall.

MUVERA demonstrated in the paper it out-performed PLAID in latency controlling for a target recall level. Some datasets achieved 99.8%+ recall some achieved (i.e. SCIDOCs with 57%) much lower. Especially with the more complex MaxSim distance calculation you don't always achieve great ANN index recall with multi-vector models.

Personally I think MUVERA will win over PLAID style approaches for ecosystem reasons. With MUVERA you can adapt any ANN index (HNSW, DiskANN, ScaNN, Faiss, etc) with just the FDE encoding and MaxSim implementation (leveraging everything already done in this area) while PLAID requires a complex 4-stage pruning pipeline.

[John Trengrove @trengrj]

I really like LEANN but it does require embedding chunks on the fly for each query (for each batch of distance calculations as you navigate the graph). For most use-cases the costs (in API calls, time, or GPUs) of creating embeddings is high enough you don't want to do this. However when paired with static embeddings (like with @minishlab's model2vec) LEANN could be a good solution for storage constrained workloads.

[Lior Alexander @LiorOnAI]

Stop storing embeddings.

A laptop can now index 60 million text chunks using 6GB, not 200GB.

LEANN, a new open-source project flips how vector search works.

𝗧𝗵𝗶𝘀 𝗶𝗻𝗱𝗲𝘅 𝗱𝗼𝗲𝘀 𝗻𝗼𝘁 𝘀𝘁𝗼𝗿𝗲 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀
Instead of saving every vector, it stores a compact graph.
Embeddings get recomputed only when a query actually needs them.

• Graph-based selective recomputation
• High-degree node pruning to keep recall stable
• No accuracy drop versus FAISS-style indexes

𝗧𝗵𝗲 𝘀𝘁𝗼𝗿𝗮𝗴𝗲 𝗴𝗮𝗶𝗻𝘀 𝗮𝗿𝗲 𝗺𝗮𝘀𝘀𝗶𝘃𝗲
Email archives shrink from gigabytes to megabytes.
Browser history fits in single-digit MBs.
A 60M-document corpus fits on a laptop SSD.

𝗜𝘁 𝗿𝘂𝗻𝘀 𝗲𝗻𝘁𝗶𝗿𝗲𝗹𝘆 𝗹𝗼𝗰𝗮𝗹
No cloud calls. No telemetry.
Everything stays on-device with zero ongoing cost.

𝗜𝘁 𝘂𝗻𝗹𝗼𝗰𝗸𝘀 𝗹𝗼𝗰𝗮𝗹 𝗥𝗔𝗚 𝗮𝘁 𝗻𝗲𝘄 𝘀𝗰𝗮𝗹𝗲
You can semantically search files, emails, chats, codebases, and live MCP sources.
All from one local index, without changing your workflow.

[John Trengrove @trengrj]

@copyconstruct I think they are still being built but people aren't hearing about them. The build vs buy pendulum has swung heavily to build with AI so you now have 50 vibe coded file systems etc with few users vs a category winner.

[John Trengrove @trengrj]

@JacobianNeuro Really interesting! Do you think the scaling improvements would hold keeping a fixed output dimension for all models?

[John Trengrove @trengrj]

At least job ads asking for 10+ years of grep experience won't be so annoying

[Antoine Chaffin @antoine_chaffin]

me: no but RAG can be done with plain old exact matching grep, it's totally fine
@mixedbreadai: rebrand search as grep
me: alright, then I guess I am doing grep now

[John Trengrove @trengrj]

@Yuchenj_UW Yann in his arguments stressed lack of physical world model and training from sensory data while Ilya focused more on LLMs not being coherent (flip-flopping, whale-a-mole errors etc) which I think makes more sense to people using LLMs day-to-day. Also timing is important.

[John Trengrove @trengrj]

Please see this notebook for details https://t.co/NzCmh9OrGm.

[John Trengrove @trengrj]

https://t.co/yxva6DiuCs

[John Trengrove @trengrj]

Link here E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker https://t.co/wY9FY3WoOM by @qiliu6777

[John Trengrove @trengrj]

The idea that an embedding model can also be a effective reranker (E2Rank) opens up a lot of interesting opportunities especially for local usage where you don't want to run multiple models.

[John Trengrove @trengrj]

@_weiping Do you still plan to release the weights for RankRAG?

[John Trengrove @trengrj]

@jxnlco @jxnlco I was actually watching one of your videos with around 200 views last week and thought the recommendations algorithm was broken.. Keep going the content is excellent.

[John Trengrove @trengrj]

@atulit_gaur If they talk about powers of 2 that is one thing, but if they talk about the history of embedding models, impact of BERT, and the hidden size of BERT-base being 768 and BERT-large being 1024 you have found a gem.