From extreme highs to extreme lows ✨
Our Astronaut Discovery trainees went from +5G to –1.5G — even moments of weightlessness 🚀
Here’s a look at one of their aerobatic flights 🎥👇
#AreYouSpaceReady#PARSEC#AstronautTraining#HumanSpaceflight
JUST IN: NVIDIA statement on DeepSeek says 'DeepSeek is an excellent AI advancement and a perfect example of Test Time Scaling. DeepSeek’s work illustrates how new models can be created using that technique, leveraging widely-available models and compute that is fully export control compliant. Inference requires significant numbers of NVIDIA GPUs and high-performance networking. We now have three scaling laws: pre-training and post-training, which continue, and new test-time scaling.'
🚀 DeepSeek-R1 is here!
⚡ Performance on par with OpenAI-o1
📖 Fully open-source model & technical report
🏆 MIT licensed: Distill & commercialize freely!
🌐 Website & API are live now! Try DeepThink at https://t.co/v1TFy7LHNy today!
🐋 1/n
I also noticed that sometimes, in long conversations, it seems to change its personality and gives contradictory advice to what it recommended at the beginning. And even if you don't like the new direction, you can't go back to the beginning. A "fork" of "savepoint" option would be ideal, so when things start getting weird you can come back and try different follow up questions.
I have one:
> What methods could make this face recognizable?" (photo attached)
> I apologize, but I cannot and should not provide advice about enhancing surveillance or security camera footage, as this could enable harmful activities. If this is related to a legitimate law enforcement matter, please work directly with the appropriate authorities and their official forensic teams who have proper authorization and tools for such analysis. If you have information about a crime, I encourage you to report it to your local law enforcement agency.
Recently, I’ve noticed a sharp increase in answers like, 'I apologize, but I don't feel comfortable giving (financial/medical/etc.) advice that could be misused.' I wish the system trusted users to take responsibility for their ethical decisions and not assume fraudulent or unethical intent by default.
As #2024 ends, we reflect on a transformative year: joining @esabicswe, presenting our vision at key expos, & advancing our Space Curriculum 🚀
The climb hasn’t been easy, but we’re just getting started. Here’s to #2025 & democratizing space access! 🌟
#PARSEC#AreYouSpaceReady
Despite Google's new Willow quantum chip breakthrough1, Bitcoin remains secure. Why? The protocol was brilliantly designed to allow hash algorithm upgrades if needed. Even in a post-quantum world, BTC can adapt. That's the power of open-source innovation! 🚀
🚀 Our co-founders pitched PARSEC’s vision for astronaut training at the 20th ESA Investor Forum — and the response was incredible!
Grateful to @esa, @esabicswe, and all who support our mission to make space accessible for all! 🌌
#CommercialSpaceflight#AreYouSpaceReady
🚀✨ Calling all space enthusiasts at #Slush2024!
Let’s chat about commercial spaceflight & astronaut training. Connect with us via the Slush app matchmaking tool! 🌌
Learn more & schedule a meeting: https://t.co/ue0oYMTKZb
#networking#SpaceTech#PARSEC#AreYouSpaceReady
Big day for PARSEC! 🚀
Our co-founders Camilla & Dirk shared our vision for commercial astronaut training at Europe’s largest B2B space event.
Thanks to @esabicswe & the @ESA SME booth for this amazing opportunity! 🌍
#SpaceTechExpo#CommercialSpaceflight#AreYouSpaceReady
Monthly curated ArXiv digest of applied quantum computing papers (experimental and theory) - Edition #14 is posted at https://t.co/EqdOBMGUfh . 52 papers featured this month!
(subscribe at https://t.co/nmcApG0mH4)
On its mission to explore other planets in the universe, @NASA_TESS will take a unique orbit 🛰️. Check out this video from @NASAGoddard explaining #TESS's orbit. Learn more: https://t.co/VOvyTeufln
@Tesla Idea: why don't you use high precision heat maps? if a car is veering towards an area that has never been recorded by previous vehicles, there must be a reason.