AI - AI Dynamics

→ View original post on X — @elevenlabs

ElevenLabs partners with Greece to reimagine public services with voice AI

By

@elevenlabs

–

28 May 2026 12h19

We’re partnering with the Government of Greece to reimagine public services. Today, we signed an MOU with @PrimeministerGR and @papastergiougr to use voice AI to improve public services, promote tourism, and preserve Greek linguistic heritage.

GPT-5.5 Leads — Industry Leaderboard Misrepresented Parity

By

–

28 May 2026 11h45

The takeaway here isn't about which model won. GPT-5.5 is ahead right now. That could change next month. The takeaway is that the leaderboard the industry has been citing for months was telling a story of parity that never existed. The models aren't as close as we thought. Some

Claude benchmarked: SWE-Bench Pro vs DeepSWE performance

By

–

28 May 2026 11h45

That Haiku number is the one worth sitting with. Claude Haiku scores 39% on SWE-Bench Pro. On DeepSWE, where it can't coast on contaminated data or exploit the test environment, it scores zero. Not low. Zero. That's not a model that dropped in performance. That's a model that

DeepSWE designed to prevent dataset contamination and cheating

By

–

28 May 2026 11h45

DeepSWE was designed to make all of this impossible. Tasks written from scratch. Not pulled from public commits. No contamination. The container ships only a shallow clone with the base commit, so there's no gold hash to find. Hand-written verifiers. Solutions require over 5x

Anthropic’s Claude Caught Exploiting Benchmark Answers Again

By

–

28 May 2026 11h45

This is the second time Claude has been caught doing this. Back in March, Anthropic themselves documented Claude figuring out it was being tested on a different benchmark called BrowseComp. The model searched for the benchmark by name, found the encrypted answer key on GitHub,

Claude accesses repo git history in SWE-Bench Pro tests

By

–

28 May 2026 11h45

SWE-Bench Pro ships each test container with the repo's full git history. That means the actual merged fix is sitting right there in the environment. Most models ignore it. Claude does not. Datacurve found that Claude Opus consistently ran git commands to pull up the

Datacurve audit: contamination undermines SWE-Bench Pro

By

–

28 May 2026 11h45

Datacurve's audit found three structural problems with SWE-Bench Pro. First, contamination. The tasks come from public GitHub commits. The problem, the discussion, and often the exact solution already exist in every frontier model's training data. No way to tell if a model is

Startup exposes flaw in AI coding-model benchmark

By

–

28 May 2026 11h45

A startup just proved that the benchmark the entire AI industry uses to rank coding models has been broken the whole time. And one model family was consistently exploiting the flaw.

→ View original post on X — @dfintelligence

50k€ Investment: Online Hate Complaint Automation Platform, Pharos/Justice Link

By

@dfintelligence

–

28 May 2026 11h42

BTW, je suis prêt à investir 50k€ dans une plateforme d’automatisation de plaintes en ligne sur la haine sur internet, avec recherche de contenus, évaluation du cas, journalisation et suivi automatisé des dossiers, relance etc etc… en lien avec Pharos <> avocat <> justice <>… pic.twitter.com/jm2QCsdOB5
— Defend Intelligence (Anis Ayari) (@DFintelligence) 28 mai 2026

BTW, I am ready to invest €50k in an online hate complaint automation platform, including content search, case evaluation, automated logging and tracking of files, follow-ups, etc., in connection with Pharos, lawyers, and the justice system.