Brief IA
›

AI completes less than one task in ten in simulated business environments

Code & Dev·Tom Levy·

AI completes less than one task in ten in simulated business environments

AI completes less than one task in ten in simulated business environments
Key Takeaways
1Agents complete less than one in ten tasks in a simulated business environment.
2Claude Opus 5.5 and GPT-6 Astra are among the models involved.
3Anthropic claims that Claude produces over 80% of its production code.
Why it matters : The experience assesses agents in a simulated professional environment that includes colleagues, projects, and conversations.

In a simulated corporate experiment, programming AI agents completed less than one task in ten. This result particularly concerns Claude Opus 5.5 and GPT-6 Astra.

Anthropic Claims Massive Use of Claude

Anthropic asserts that Claude produces over 80% of its production code. In standard evaluations, these agents approach top performance; tests such as SWE-bench are nearing saturation.

La lettre du soirGratuit · 19 h

Le brief IA que les pros lisent chaque soir

Les 7 actus IA du jour, décryptées en 5 min. Gratuit.

Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.

Choisissez votre rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

The Simulation Provides Colleagues for the Agents

The experiment assigned them roles as digital employees in a fictional software company, a scenario presented as a first. Their environment included colleagues as well as boards dedicated to projects and archives of conversations.

Brief IA — L'actualité IA en français

L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.