XCSme

↗ HN profile [ 74.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I thought I was going crazy, trying to use Gemini 3.5 Flash to rate some answers, but it kept giving 7 instead of 10 for correct answers. Apparently once you add a "Grading criteria" text, the model collapses into a…

  2. I kept trying to use their M2.5 model and now they released M2.7, but they are TERRIBLE. See this comparison I made:…

  3. Why Not Boost? (twitter.com)
  4. My last submission didn't gain any traction, and since I improved the platform A LOT. I am really happy with how it turned out, I am really focused on small UX things, on desktop it's quite fun to just play around,…

  5. Hey HN, Like many of you, I'm tired of public AI leaderboards that mostly recycle the same saturated/overfitted benchmarks (MMLU, HumanEval, etc.) and often miss fast/cheap variants or real daily pain points. A couple…

  6. Over the last 10 years, I kept trying to run various ad campaigns for my products. NEVER was I able to get any sale from ads, and it seems like all traffic is bot traffic. I am not sure if I'm doing anything wrong, or…

  7. Bolt v2 (twitter.com)