Fancy harnesses make coding agents more expensive but not better, study finds
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step. The article Fancy harnesses make coding agents more expensive but not better, study finds appeared first on The Decoder.
Get smart on it
A coding agent pairs a language model with a harness, which consists of the system prompt, tools, and context management that enable the model to work inside a code repository. Researchers tested whether different harnesses produce meaningfully different results and found that switching between harnesses changes performance about as much as simply running the same setup twice, yet the cost can triple depending on which harness is used. The difference in cost comes primarily from the size of the system prompt and tool descriptions rather than from actual performance improvements. The study suggests that earlier advertised performance gaps between harnesses were largely measuring noise rather than real differences in capability.
Explainer: The 90% That Matters: Why Your Agent's Harness Beats the Model
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Claude Science tackles deadly scorpion stings by designing protein binders from scratch
Anthropic's Claude independently designed protein binders targeting deadly scorpion neurotoxins. Out of more than 318,000 designs, 211 were tested in the lab. Seventeen met the criteria, and the two strongest bind extremely tightly to Cn2, a toxin from a Mexican scorpion. Whether they actually work as antivenom remains an open question. The article Claude Science tackles deadly scorpion stings by designing protein binders from scratch appeared first on The Decoder.
Also reported by The Verge
Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 at up to 8x the speed
Diffusion language model startup Inception AI Inc. today released Mercury 3, its new flagship model. In the company’s own benchmarks, Mercury 3 beat OpenAI Group PBC’s GPT-6 Luna and Anthropic PBC’s Claude Haiku 5.5 on eight of 12 tests at four to eight times their speed. The release takes on the main doubt about Inception’s […] The post Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 at up to 8x the speed appeared first on SiliconANGLE.
Also reported by The Decoder
Microsoft says its AI tool is better than doctors at diagnosing conditions
Microsoft AI chief Mustafa Suleyman. | Getty Images For years, AI leaders have touted healthcare as one of the clearest examples of where their technology will improve lives. Now "it is finally here," Microsoft AI CEO Mustafa Suleyman tells The Verge. The company claims to have developed an AI-powered tool it says can diagnose conditions up to four times more accurately than human doctors. The findings, published Thursday in one of the world's most prestigious journals, Science,
Microsoft’s Mustafa Suleyman says its AI outperforms doctors on hard cases as he chases ‘medical superintelligence’
Microsoft’s new AI diagnostic system beat generalist doctors on hard cases, according to a study in Science. But most of the improvement seems to come from the AI models underneath, not from Microsoft’s system itself.
Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.
A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90% of nearly 500 election races.
OpenAI's GPT-5.6 Sol and Google's Gemini 4 Argon found critical PHP flaw affecting millions of websites
OpenAI's GPT-5.6 Sol discovered a critical PHP vulnerability as part of the Patch the Planet initiative that could affect millions of websites. Security firm Wiz independently found the same flaw using Google's Gemini 4 Argon. OpenAI warns that the same AI capabilities that find vulnerabilities can help attackers too. The article OpenAI's GPT-5.6 Sol and Google's Gemini 4 Argon found critical PHP flaw affecting millions of websites appeared first on The Decoder.
Also reported by TechCrunch