Viewing profile — mixtureoftakes
mixtureoftakes
HN member- Joined
- Thu, Jun 06, 2024, 9:21 AM UTC
- HN karma
- 106
- Public activity
- 71 items
- HN profile
- View on Hacker News ↗
About mixtureoftakes
Recent public activity
-
comment
Comment #49068056
thank you embedding-shape
- comment
-
comment
Comment #48976471
What was the harness used? And yeah surprised about such prompts not being downright blocked, even with the cybersafety verification"
-
comment
Comment #48829470
How do you have access?
-
comment
Comment #48782772
They seem to be serving it at 3x the price while also struggling with maintaining uptime on openrouter; while the vercel router advertizes even bigger speeds but has no clear uptim…
-
comment
Comment #48624271
yeah and lets not forget codex and glm have subscriptions too, with even more usage per dollar
-
comment
Comment #48436153
We have notebooklm at home? Is there any comparison between these two, looks nice
- comment
- comment
-
comment
Comment #48274079
insane levels of slop, so bad it almost feels intentional
-
comment
Comment #48224198
So they made a phone?
-
comment
Comment #48206760
I'm more excited for qwen3.7 9b and 72b, these are usually so good for their size
-
comment
Comment #48198374
also parsing is harder + so much more of the new data is being generated by ai itself. still the cutoff is very much concerning and inconvenient
-
comment
Comment #48197011
benchmarks look REALLY good, the price hike is big but it also beats sonnet 4.6 in every discipline?
- comment
-
comment
Comment #48178803
you ever look on a title and just immediately know that its going on the frontpage + staying there
-
comment
Comment #48142487
if you're not checking citations in the paper youre publishing AND trusting a non SOTA, hallucination prone ai model to come up with sources for it, its probably for the best of ev…
-
comment
Comment #48140232
7b mistral is quite outdated. On a 12gb 4070 you can run qwen 3.5 9b q4km or qwen 3.6 35b, the latter will be a lot smarter but also a lot slower due to ram offload. Try both in lm…
-
comment
Comment #48135761
anthropic really needs to just make a great, personalized customer support experience where you get a couple dollars worth of opus credits that has some authority and ability to he…
-
comment
Comment #48111738
Great points. Using their printer "rooted" or with custom firmware seems like a decent compromise to me, kind of like what graphene is doing with pixels
-
comment
Comment #48078782
wow! curious about your workflow for running all these accounts. different harnesses in parallel? manually switching in codex? 5.5pro only? what works for you?
-
comment
Comment #48072692
please, sign up for a paid plan of either chatgpt or claude. gemini is while close, still noticeably behind you deserve opinions shaped by interactions with the best tools that are…
-
comment
Comment #47886871
more like weekly or almost daily, gpt 5.5 was literally 12 hours ago
-
comment
Comment #47728697
who are you.
-
comment
Comment #47725113
unpopular opinion but i think it's written quite well