earth2mars

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.

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!

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

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 can see Claude