Barb

[juggernaut @curlysaarthak]

jane street has some interesting blogs
too bad it would take a week to understand each

https://t.co/Z00MpzUDiU

https://t.co/qMXCn5wO8J

https://t.co/OdSGZzzYSY

https://t.co/kTgOenAhVT

[Yangzhen Wu @yangzhen04]

Static benchmarks are dying — they tend to get saturated quickly.

Evaluation and training data should co-evolve with frontier models.

We released BenchEvolver — a framework that automatically evolves saturated problems into harder, verified tasks for evaluating frontier models, which can also serve as useful self-improvement signals for RL.

New work from UC Berkeley @berkeley_ai @BerkeleyRDI @BerkeleySky

Project Page: https://t.co/PL1KpGyd87
Paper: https://t.co/gBQOXrZbAV

[Owain Evans @OwainEvans_UK]

New paper on truthful AI!
We introduce a definition of “lying” for AI
We explore how to train truthful ML models
We propose institutions to support *standards* for truthful AI
We weigh costs/benefits (economy + AI Safety)
(w/ coauthors at Oxford & OpenAI)
https://t.co/9QII1WXFqw

[David Bau @davidbau]

We really don't understand AI lying fully.

What happens when an AI lies? How can you best detect it? Can white-box detectors beat black-box ones in an adversarial setting?

It is an ongoing interpretability challenge.

We'd like you to try your hand at it. Join our contest!

[David Bau @davidbau]

But AI lie detection is hard and remains a central research challenge.

Recent research suggests that simple probes can pick up on neural "tells" that reveal when it is lying, even when the output looks clean.

https://t.co/zTQIaNcpag
https://t.co/wVCwKlGVIr

[Aaron Scher @aaronscher]

Interestingly, training compute for open-weight AI models doesn't appear to have grown very much in the last 2 years. Llama 3.1-405B (and derivative models) still holds the record 2 years later. Data from Epoch. https://t.co/DWBq23xNAt

[Garry Tan @garrytan]

https://t.co/0hcNuYzbMd

[BLVCKL!GHT @BLVCKLIGHTai]

https://t.co/WmpxZ0cmx4

[ModelScope @ModelScope2022]

Introducing Q-Judger and Qwen-Image-Bench, an automated T2I evaluation suite from Qwen team. Apache 2.0. 🤖 https://t.co/hv3R6iU9UX

Q-Judger is built on Qwen3.6-27B with thinking mode. Input prompt + image, get structured JSON scores across 5 dimensions: Quality, Aesthetics, Alignment, Real-world Fidelity, Creative Generation. Spearman ρ = 0.92 vs human expert rankings. Trained on 130K+ bilingual pairs supervised by 80 professional annotators from art academies.

[Adam Chalmers @adam_chal]

Announcing Zoo's completely redesigned sketch mode! You can sketch complex 2D geometry SO much quicker now. So many improvements:

- Constraint solver
- Trim tool (remove parts of intersecting geometry)
- Select regions (overlapping 2D spaces) for extrude

It's a big upgrade.

[Luba Elliott @ CVPR @elluba]

The #CVPR2026 Art Gallery is now live 🥳

114 artworks using or about computer vision, presented online and as videos and installations at the @CVPRConf in Denver between 5-7 June next week 😍

Check it out https://t.co/XTGoCWaDV8

#creativeAI #AIart

[Serena Ge (Datacurve) @serenaa_ge]

Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks.

On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.

[Director Michael Kratsios @mkratsios47]

You can’t make scientific breakthroughs without the tools to pursue them.

Big news from @NSF: $250M to restart and supercharge the SBIR/STTR program, including a new $40M pilot for next-gen scientific instrumentation.

America’s small businesses will build the platforms that define discovery.
https://t.co/a0z16TawAy

[ангел𓂀𓋹🪽𖤓 @cleomythra]

‘Hands weaving magnetic-core memory, IBM, Poughkeepsie, New York,’ 1956. Photograph by Ansel Adams.

[Zelda @zeldapoem]

Written by @ulkar_aghayeva: https://t.co/Vbo3B1YpPn

[PyMC Labs @pymc_labs]

The radar plot is the most popular chart in football analytics. It might also be the least effective.

Chris Fonnesbeck breaks down why and builds the replacement: https://t.co/DeOScY3tfh

#SportsAnalytics #DataViz #Bayesian

[Vlad Feinberg @FeinbergVlad]

How to land a job at a frontier lab

https://t.co/oHIqLgBMbC

[Charles 🎉 Frye @charles_irl]

Inference isn't everything, but it does require a new stack -- not Kubernetes, not SLURM.

At @modal, we dove deep to build that stack.

In this blog post we explain how, from compute management & cloud-native cacheing to CRIU & GPU checkpointing.

https://t.co/DQ4wvuXjre

[Thariq @trq212]

https://t.co/MXt5XS4xBX

[piterpasma @piterpasma]

debug view

#generative #genartclub