Re:Show HN: Dayflow – A git log for your day
by yewenjie on Thursday September 25, 2025 @12:15AM
(#45369222)
I would not be comfortable sending my bank info passwords and all sorts of other sensitive data that I input and see on my screen to Gemini. How much is the qualitative performance difference with a local model?
[ Parent
| on HN ]
Re:Show HN: Dayflow – A git log for your day
by jerryliu12 on Thursday September 25, 2025 @12:22AM
(#45369250)
If I had to put a grade on my own experience and evals, Gemini 2.5 pro produces A- results and qwen2.5vl is maybe like B-/C+. Obviously everything's nondetermistic, so it's hard to guarantee a level of quality.
I'm reading through papers that suggest it should be possible to get SOTA performance on local models via distillation, and that's what I'll experiment with next.
Re:Show HN: Dayflow – A git log for your day
by zbrw on Thursday September 25, 2025 @09:04AM
(#45372215)
Any insights on qwen-3 omni yet?
Re:Show HN: Dayflow – A git log for your day
by jerryliu12 on Thursday September 25, 2025 @03:12PM
(#45377500)
Looks awesome, but a 30B model is too big. Vast majority of people probably have 32GB of RAM or less unfortunately.
Re:Show HN: Dayflow – A git log for your day
by CIPHERSTONE on Thursday September 25, 2025 @10:30AM
(#45373033)
Also, if your not using an enterprise edition of gemini where your data is not used for model training, your sensitive data prompts and responses is 100% available to google.