CommonSenseOnMars
5.7K posts
CommonSenseOnMars
@CommonSenseMars
Future Martian ancestor
Mars Katılım Haziran 2024
4.1K Takip Edilen963 Takipçiler
Happy Friday! We've reset everyone's 5-hour and weekly rate limits.
English
@ashleevance @alexandr_wang If only there was a podcast for him to go on 🤔
English
That @alexandr_wang fella hasn't done an interview in a very long time . . . .
English
@OpenAI @jadenitripp ChatGPT voice mode skipped again😭
English
Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents.
Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold.
Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.
English
1) heavy js sessions with app browser preview jams up entire codex app, 2) custom pets should be able to go beyond the 8 x 9 sprite sheet if user asks, 3) asset/progress element that appears on right side hover interferes when mouse is near play/stop area of prompt bar too often, 4) my remaining usage is too low 😋
English
@Dimillian more of a tangent, but for the updated UI, moving the mouse close to "send" or "steer" too easily opens up the artifact element on the right, preventing clicking of send or steer
English
A new feature sneaked in the Codex app’s latest update. You can now do /side (or use the ... menu) to spawn a side chat! Useful when you're deep in a thread and want to have a side question in the current context!
English
@ajambrosino "Even better slides and sheets" say more?
English
Codex for everything:
- Dynamic UI for the task at hand
- 20% faster computer & browser use
- Even better slides and sheets
- Annotate in browser, artifacts, and code
- Easier to get started
- Cleaner design across the app
- Performance improvements
- (no clunky handoff/switching)
English
@thsottiaux @jadenitripp @Mugilan_SS @OpenAI Codex is great. Who is doing similar for the ChatGPT apps ? Seems hard to give feedback for that side.
English
@Mugilan_SS @OpenAI It’s the small things. When we designed this the tradeoff was between a good experience or optimize for margin and not allow to draw more usage than you technically have.
We chose to optimize for the experience as it’s really annoying to have your agent interrupted midway.
English
@ClaudeDevs I would like to read this thread but "An image in the conversation exceeds the dimension limit for many-image requests (2000px). Run /compact to remove old images from context, or start a new session."
English
In the last four Claude Code CLI releases, we’ve shipped 50+ stability and performance fixes.
Faster resume, stable auth, lower memory, fewer hangs: 🧵
English
@Nomandsign @ClaudeDevs Yes. This keeps stopping my sessions.
English
@Noahpinion Overblown and this constant push about ai bioterror incentivizes making the models even less useful to stem researchers and students than they already are (eg american ai models censoring info that is already in papers, google, and widely practiced in the field)
English
Everyone seems to be scared of either:
* job loss
* rogue superintelligence
* slop
* data center water use (LOL)
No one seems to be paying attention to the biggest AI threat, which is BIOTERRORISM
Tyler Rogoway@Aviation_Intel
One of many MANY alarming examples of what’s to come. Why isn’t there work on regulation or even attempt at some sort of control regime, domestic and international, on what is likely to be the most powerful and unpredictable weapon ever created? Just oh well no stopping it?
English
@thsottiaux Started getting this for the first time... an emergency /compact got it back on track
English
@adele__li Congrats on the image 2 launch! It's great. Though fyi, the image tool seems to break often when used in chatgpt projects
English
@xai That's cool. Now, needs voice design, voice cloning.
English
Introducing Grok Voice Think Fast 1.0
A state-of-the-art voice model built for complex, multi-step workflows with snappy responses and high accuracy.
It takes the top spot on the Tau Voice Bench and handles real-world messiness like noise, accents, and interruptions better than any other model in the world.
x.ai/news/grok-voic…
English
Separately, we’ve also heard reports of issues with Opus 4.7 in Claude Code. The team is working on those and we’ll share more as we roll out improvements over the coming days.
English
We’ve been looking into recent reports around Claude Code quality issues, and just published a post-mortem on what we found.
ClaudeDevs@ClaudeDevs
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
English
