News for hackers. Stuff that matters.

MukundMohanK

Re:Why build a domain-specific agent for front end tasks? on Thursday July 31, 2025 @10:47AM (#44746251)
Re:domain-specific solutions inevitably outcompete general-purpose ones. Certainly not the case for coding agents.

Vertical software won because GUIs were scarce. General LLMs are winning because context is abundant.

Re:New #1 open-source AI Agent on SWE-bench Verified on Thursday May 22, 2025 @08:04AM (#44061208)
Reality is here whether we like it or not - https://fred.stlouisfed.org/graph/?g=1DEP0
Re:New #1 open-source AI Agent on SWE-bench Verified on Thursday May 22, 2025 @07:34AM (#44061006)
Between last April and now, swe-bench scores have gone up from 25%-70% for.

Sure, they're being overfitted to the dataset. But with most performing similarly across even the hardest of 3rd party benchmarks, think frontier math back in Nov and now, we're closer than ever to a specialisation shift.

Hard to say at what % but once code reviews get better its likely 2025 is the last year SWE is a sought after job * demand and supply both