IMO DeepSeek v4 demonstrated utter confidence and competence by not benchmaxxing, not focusing on some BS final run cost, not even spending inference-optimal compute. just showed up, demonstrated SOTA long context efficiency techniques (CSA, HCA, mHC, flash at 8% cost of pro,
@swyx
-
AIE Now Run by Agents Says Unreleased Talk
By
–
AIE is run by agents at this point. full unreleased talk here
-
Article Quality Issues: Technical Depth and Advertising Concerns
By
–
gentle feedback that the article started strong but also degraded in quality as it went on and being light on technical detail (probably ai written) and came across more like an ad. shouldnt have had to read @mccatec
's comment to get to the crux of the issue. -
Staying Passionate About Technology Through Continuous Innovation
By
–
i think one thing that has served me well as I havent sat still enough to get grumpy. always so much to sincerely fall in love with tech
-
Viability threshold below one percent in AI systems
By
–
what makes you beleive <1% is viable? we havent even seen anyone under 2% have we?
-
Engineer Challenges the True Cost of Code Development
By
–
wow another engineer on the “code is not cheap” train
-
Product Manager vs Engineer Perspectives in AI Implementation
By
–
fun to think about what the pm thinks vs what the engineer thinks in this scenario