Amazon’s SWE-PolyBench just exposed the dirty secret about your AI coding assistant

Credit: VentureBeat made with Midjourney
Amazon launches SWE-PolyBench, a groundbreaking multi-language benchmark that exposes critical limitations in AI coding assistants across Python, JavaScript, TypeScript, and Java while introducing new metrics beyond simple pass rates for real-world development tasks.Read More

Commentaires

Enregistrer un commentaire

Posts les plus consultés de ce blog

Eclipse Foods inks deal with Whole Foods for its plant-based ice cream

With demand for plant-based meat alternatives at an all-time high, Eclipse Foods is no doubt hoping to do for ice cream what companies like Impossible and Beyond have managed for the hamburger. Pre-pandemic, the company announced select retail availability in New York and its native San Francisco, and now it’s expanding coverage with a high-profile retail partnership. Launched in early 2019, the company has raised nearly $16 million to date, including funding from YC. In an earlier interview with TechCrunch , CEO Aylon Steinhart noted that the company looks to differentiate itself from other plant-based foodstuffs with a simple approach to provide an alternative food source. “We’re not using any expensive biotech to get to where we’re going,” the exec noted. “We take plants and we use our world-class expertise in functional plant proteins and how they work to blend plants together in a quite simple way.” Eclipse is still looking to mimic dairy-based ice cream more directly. “Enteri...
Lire la suite

Payhawk raises $112M to better compete in the heated corporate card race

If you’ve followed corporate card and spend management startups in the U.S., you might be familiar with Brex and Ramp . Payhawk is also offering an all-in-one financial management solution for businesses, but with a focus on European customers. And the company just raised a $112 million Series B round at a $570 million valuation. Greenoaks is leading the round, with all existing investors participating once again, such as QED Investors and Earlybird Digital East. Payhawk wants to replace several services that companies use to simplify their financial stack and make things work better together. Customers get their own account with a dedicated IBAN. They can connect this Payhawk account to their existing bank account to load and withdraw funds. After that, you can use Payhawk for all things related to payment. Customes can issue virtual and physical cards for employees with a set rules, such as a team budget or an approval workflow. This way, employees don’t have to pay with their p...
Lire la suite