New MIT and Sakana AI framework uses an LLM judge to cut evaluation costs for self-improving coding agents

MIT and Sakana AI's SIFT framework reduces coding agent evaluation costs by using a language model to rank candidates, ...
Crypto Briefing

MIT and Sakana AI’s SIFT framework cuts the cost of judging self-improving coding agents

MIT and Sakana AI's SIFT framework hit 35.1% on Polyglot in 30 steps and ran a full search for about $34, roughly one-tenth ...
RS Web Solutions

MIT’s Alex Zhang Claims OpenAI and Anthropic Coding Agents Are Essentially Identical

MIT’s Alex Zhang reveals why OpenAI and Anthropic coding agents are basically the same, sparking debate in AI development ...
Ars Technica

"Don't ever use recursion in production code"

At a job interview on Friday, I had to write code, and one of the things that came up when we were talking about implementation of a concept was recursion. The director of the group said to me "Don't ...
thenextweb.com

Anthropic says Claude writes 80% of its own code and the world needs a plan to hit the brakes

Anthropic reveals that Claude now writes over 80% of its production code, with engineers shipping 8x more code per quarter than in 2024. The company’s new Anthropic Institute paper maps the path to ...
THE DECODER

Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness

SoL-Pi cuts coding agents' token usage by up to 49 percent with little change in performance by optimizing the control layer ...
Ars Technica

"Don't ever use recursion in production code"

I have seen recursion code implode on itself on the JVM before. In this case, we caught the annoying stack overflow problem before it went into production and I had to work a good number of hours in ...