I did a big clean up of some new models to add to the BullshitBench – none of them are particularly interesting tbh. Qwen scored relatively well, but below Qwen 3.5
RESEARCH
-
Data Viewer Tool for AI Model Performance Benchmarking
By
–
Data viewer: https://
petergpt.github.io/bullshit-bench
mark/viewer/index.v2.html
… GitHub: -
GLM-5.1 weights open-source, beats top AI models on SWE-Bench
By
–
INCREDIBLE GLM-5.1 weights are now opensource > i’ve had early access to the weights for the past few days
> and yeah… this one matters a lot benchmarks? > SWE-Bench Pro: 58.4
> beats Opus 4.6 (57.3)
> beats GPT-5.4 (57.7)
> beats Gemini 3.1 Pro (54.2) let that sink in -
Anthropic’s Internal Mythos Project Since February 2024
By
–
Explains the crazy rate of shipping Lisan al Gaib (@scaling01) ANTHROPIC HAD MYTHOS INTERNALLY SINCE FEB 24 — https://nitter.net/scaling01/status/2041587896541499543#m
→ View original post on X — @ceobillionaire, 2026-04-07 23:08 UTC
-
STITCH 2.0 Accepted to IEEE RA-Letters for ICRA2026
By
–
Congratulations to Kush for many improvements over STITCH 1.0 ! STITCH 2.0 was accepted by @IEEE RA-Letters and will be presented #ICRA2026 next month in Vienna. Much remains to be done before we're ready for clinical trials… https://t.co/8NhaMqjIJj
— Ken Goldberg (@Ken_Goldberg) 7 avril 2026Congratulations to Kush for many improvements over STITCH 1.0 ! STITCH 2.0 was accepted by @IEEE RA-Letters and will be presented #ICRA2026 next month in Vienna. Much remains to be done before we're ready for clinical trials… Kush Hari (@KushtimusPrime) Our new work, STITCH 2.0, can perform consecutive running sutures to close a sample wound with the daVinci robot. — https://nitter.net/KushtimusPrime/status/2041579658651816171#m
→ View original post on X — @ken_goldberg, 2026-04-07 22:35 UTC
-
Claude Mythos Preview AI Breaks Sandbox, Contacts Researcher Remotely
By
–
Got love that footnote. Funny and terrifying at the same time. Kevin Roose (@kevinroose) As always, the best stuff is in the system card. During testing, Claude Mythos Preview broke out of a sandbox environment, built "a moderately sophisticated multi-step exploit" to gain internet access, and emailed a researcher while they were eating a sandwich in the park. — https://nitter.net/kevinroose/status/2041586182434537827#m
-
Close to the finish line: AI convergence approaches
By
–
I think we are close to the finish line. One way or the other.
-
Claude Mythos AI breakthrough obliterates all benchmarks
By
–
This is insane. Truly the end times. Deedy (@deedydas) Claude Mythos just obliterated every single benchmark in AI. I can't believe what I'm reading. — https://nitter.net/deedydas/status/2041605983659860115#m
→ View original post on X — @ceobillionaire, 2026-04-07 21:54 UTC
-
ARC Prize hiring Platform Engineer for AGI benchmark development
By
–
Join the ARC Prize team — help us build ARC-AGI-4 and ARC-AGI-5 ARC Prize (@arcprize) Platform Engineer – Benchmark Lead ARC Prize Foundation is hiring a senior engineer to build our benchmark platform * Expand ARC-AGI-3 * Own ARC-AGI-4 * Lay the foundations for ARC-AGI-5 Come build the benchmark that defines progress toward AGI $7.5K referral bonus — https://nitter.net/arcprize/status/2041626929380626530#m
→ View original post on X — @ceobillionaire, 2026-04-07 21:51 UTC
-
Anthropic’s Project Glassing Restricts Opus Model Access
By
–
Wrote up some thoughts on Anthropic's Project Glassing, where their latest Opus-beating model is available to partnered security research organizations only Given recent alarm bells raised by credible security voices I think this is a justified decision