earth2mars
earth2mars on Hacker News
This is awesome. I have no music knowledge. and my dad recently learning flute and was asking me to build something like this for him to practice. You gave me an inspiration and I built this (me asking claude to build similar to yours). I think what I built is absolute garbage but its only decently good because of what you did. here it is.
https://veeragoni.github.io/flutewizard/I hope you take it positively and I am hoping community contributes to the flute sounds and make it better and right.
what if the labs create synthetic training data saying this site is a honeypot and trying to figure out if the model is trying to escape?!
And it is open source, so you can check all the privacy and security features built in. We don't collect any information. You don't even need to sign up to use.
Posted by
earth2mars on Saturday September 05, 2026 @03:30PM
from the show-hn dept.
https://chatpanel.net/
Privacy first AI Agent that integrates with any model provider, any CLI Agent like Codex, Claude and webllm - now available on Firefox, also available on chrome and edge.
The best part about this one is all your notes, chats and meetings (yes, it can capture the transcription from your zoom, teams, google meet and webex meetings as you attend from browser) and helps you to search across using...
It has ton of other features packed. Meeting Assistant is the number 1 use case I use at work. It further helps search across meetings, chats. It even has a note taking directly in the browser. Everything local, in your browser. you can backup stuff locally. integrate with any model provider (in-browser, locally hosted or cloud hosted), agents (codex, claude code, opencode etc), amazing privacy features (anonymization, pseudonymization) to protect your personal data before it reaches models , better web search, official mcp hub integration, voice to text without internet via STT models, writing assistant in note taking. graph search across meetings, notes and chats. better browser control - try it on excalidraw by enabling Act on page - it just does wonders. auto suggest ideas when you configure local models, skills. its great value and my daily driver get work done!
Posted by
earth2mars on Saturday August 15, 2026 @12:59AM
from the show-hn dept.
https://chatpanel.net/
chatpanel is a browser side panel that helps with in-browser meetings (Zoom, Teams, Google Meet, Webex) to capture the meeting transcription live, able to answer questions with integrated AI models, agents. Its the best way to experience meetings. All, privacy at the core of it in anonymizing data before it goes to AI models. Try it to experience the power of it.
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 happening. you can ask any question about the meeting while the meeting happening and chatpanel will use configured AI agent/llm provider to answer it. Towards the meeting end it can summarize. the best part is you can ask all sorts of questions after meeting ends which is missing from out of the box meeting features provided by the meeting provider. It depends on the closed captions being enabled and capture that as live scribe. I am planning to add browser audio caption feature as well in the future
Posted by
earth2mars on Tuesday July 21, 2026 @07:56AM
from the show-hn dept.
https://chatpanel.net/
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 and I am a 100x engineer now.A few features to highlight.- You bring your own Agent (Codex, claude code etc) or local models or in-browser models or remote models
- A live meeting assistant. You got to try to this to...
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 I was working a project that supports bunch of models and the model said only Claude can do it start writing code that doesn't work with codex, opencode, pi etc. Finally, when I switched to Codex, everything worked. To me, they are controlling the narrative. This is Opus 4.8 vs GPT 5.5.
I can't believe I would say this. I TRUST OpenAI more than Anthropic. They try to play best actor but they are manipulating the behavior of the model in the name of guardrails/interpretability.
That is why I refuse to build anything that works with Anthropic models as the backend. Because, when they want to shut you off, they can do it by just making model less reliable in your product than their offering!
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
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 millions of lines of code) vs Claude Fable/Opus which does only what is been told. while codex covers all sorts of edge cases. Frankly, I am not going to miss a thing if they stopped Fable.
This should be the top post. Not Anthropic or OpenAI marketing plots. This is existential.
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 the world than GPT 5.5 or similar ones. I would say just go and try this model for serious work and see the marginal difference. the model wins in some cases and loses in many others. so, what is this all about? hype!
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 in getting things resolved). I stopped using claude mostly and having a blast with Codex 5.3. looking forward to 5.4 in codex.
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.
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 and purpose - coding?)
Yes it did well. Also some other word problems it did well too. Reasoning seems good. But maybe not a great code model
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, where people do that, they are passionate about and not have to worry about basic means and even some wants (entertainment, comfort living etc). a world of abundance for everyone where people just do what they are super passionate about. will AI help towards that or not is a big question.
How CoreWeave(wand) a competitor? I think they are a partner in in infrastructure.
Posted by
earth2mars on Wednesday November 19, 2025 @01:59AM
from the show-hn dept.
https://blog.tldrversion.com/posts/google-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 orchestration. Its so meta, that I wrote about using it. Its quirky, but fun.
I used exactly the same prompt this site uses. Nothing else.
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 banging to show better value
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 thing here.
oops. search in page is not working! (command+F)
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 providers can't figure out how they can make money. but seems like with agents workforce, shopping, ads, adult content stuff that OAI is going after, they seem to be after making money. I can see 20k yearly subscriptions coming soon for enterprises once this tech is reliable enough than a 200k employee or at least pair up with a 400k employee with 5, 20k agents to do 6x work than spending 400k+200k*5.