Viewing profile — earth2mars
earth2mars
HN member- Joined
- Mon, Feb 12, 2018, 10:45 PM UTC
- HN karma
- 177
- Public activity
- 159 items
- HN profile
- View on Hacker News ↗
About earth2mars
No profile information was provided.
Recent public activity
-
comment
Comment #48992018
There was question about how live meeting assistant works. 1/ you have to use the browser version of the meeting (not native apps) and have the chatpanel open while the meeting hap…
-
story
Show HN: ChatPanel, A Privacy-first AI Agent browser side panel
I needed an AI agent that understands my work better (meetings, notes, chats and lives where I access the web) and gives me flexibility to use the model of choice. So, I built this…
-
comment
Comment #48636439
The worst part of Opus that I dont like is they control what you can/can't do. the guardrails that they do in the name of interpretability where you steer you. Last couple of days …
-
comment
Comment #48581787
And it's really good and fast. Have tested with bunch of odd photos on what is happening. Overall the training set seems large enough to know what's what and where
-
comment
Comment #48513406
I used codex 5.5 and Claude. I pay for Claude from my pocket. I use Codex at work. I can confidently say Codex 5.5 high is much better in going through long code bases (couple of m…
-
comment
Comment #48513052
This should be the top post. Not Anthropic or OpenAI marketing plots. This is existential.
-
comment
Comment #48512890
as someone who uses these models day in out, i can confidently say its more of a marketing gimmick than anything else. don't get me wrong, the model is great, but nits no out of th…
-
comment
Comment #47935727
I can see Claude
-
comment
Comment #47265942
I am actually super impressed with Codex-5.3 extra high reasoning. Its a drop in replacement (infact better than Claude Opus 4.6. lately claude being super verbose going in circles…
-
comment
Comment #47094588
The only reason I was sticking to Android for years is this. And I think there is no moat for Android. I would rather switch to iOS if both platforms are same restrictive.
-
comment
Comment #47089012
When you say quorum what do you mean? Is it like an agent swarm or using all of them in your workflow and independently they perform better than opus? Curious how you use (tooling …
-
comment
Comment #47072950
Yes it did well. Also some other word problems it did well too. Reasoning seems good. But maybe not a great code model
-
comment
Comment #46653637
BAML
-
comment
Comment #46621767
https://blog.tldrversion.com/ - vibe coded to the most part
-
comment
Comment #46356896
not a communist, but the communist manifesto articulated this problem very well in people end up doing work that does not matter to them because of capitalism. imagine a world, whe…
-
comment
Comment #46147620
How CoreWeave(wand) a competitor? I think they are a partner in in infrastructure.
-
story
Show HN: I blogged about Google Antigravity using Antigravity
TIL about Google's Antigravity. a new AI Agents experience on top of existing tooling (A VSCode fork IDE, Agentic Chromium based browser and Electron based UI for Agents orchestrat…
-
comment
Comment #45933971
I used exactly the same prompt this site uses. Nothing else.
-
comment
Comment #45931455
https://gemini.google.com/share/00967146a995 works perfectly fine with gemini 2.5 pro
-
comment
Comment #45687681
I have a feeling the Trainium thing might get scrapped at some point of time as its probably not worth their effort in trying to retrofit. I assume AMD probalby at their doorstep b…
-
comment
Comment #45659777
duh! isn't that obvious. is this some students wanted a project with pretty graphs on writing experience?! I am not trying to be cynical or anything. just questioning the obvious t…
-
comment
Comment #45659107
and it works now!
-
comment
Comment #45659038
oops. search in page is not working! (command+F)
-
comment
Comment #45607294
all-in on AI infra. figuring out is an interim issue as the technology is moving fast while it is still early in capabilities of the models. But, bubble can only burst of the model…
-
comment
Comment #45420052
cert error