Cyan @RoySadaka

Director of AI @TolunaCorporate Israel Joined December 2009

Tweets

59
Followers

150
Following

74
Likes

79

Cyan @RoySadaka

a month ago

@thsottiaux @thsottiaux @ajambrosino Congratz on Sol/Terra/Luna release! Have a quick look at this optional improvement x.com/RoySadaka/stat…

Codex would be much better with a "consolidate side chat" option. I use /Side a lot, but often need to bring that context back to the main thread. Right now I ask the side thread for a full summary/plan, then copy-paste it manually. Would be great if Codex could do that

0 0 0 870 0

0 0 0 757 0

View Details

Cyan @RoySadaka

a month ago

0 0 0 870 0

View Details

Cyan @RoySadaka

3 months ago

@thsottiaux I use `/Side` a lot and often need to bring side-thread context back to the main thread with: “Give a full plan/summary so we can return to the main thread, assume it doesn’t know what we discussed here.” Which I then copy-paste to the main. A “Consolidate” button maybe?

0 0 4 515 0

View Details

Cyan @RoySadaka

3 months ago

@OpenAIDevs A step towards native CCC, love it! In CCC i used smashing the ‘c’ key 3 times to invoke codex to grab a screenshot and the current text so suggest completion Thx @OpenAIDevs ! github.com/RoySadaka/casu…

0 0 2 1K 1

View Details

Cyan @RoySadaka

3 months ago

@OpenAIDevs @OpenAIDevs any chance you’d consider building something like CCC natively? We’d love to be able to summon Codex from any textbox and have it understand the app/context I’m in. github.com/RoySadaka/casu…

0 0 0 305 0

View Details

Cyan @RoySadaka

3 months ago

Codex never ceases to amaze me. I'm a Mac user, so my Windows troubleshooting skills are… meh. I had a Surface Book 2 sitting dead for over 2 years, battery dead, hard-resetting a few minutes after every boot. Today I thought, why not give Codex a shot? Plugged it in, barely managed to install Codex, and it diagnosed + stabilized the machine through 5 more crashes mid-process. It's now a huge tablet for streaming, browsing, and casual online games for the kids. It almost went to the trash 😅 Wow, #Codex. Wow. Attached is the conversation dump: gist.github.com/RoySadaka/c581…

0 0 0 87 0

View Details

Cyan @RoySadaka

3 months ago

@thsottiaux Eventually I overcame it by moving the images to ephemeral session and consolidating to the main session texts only, which is better (much faster) regardless for the CCC utility, but the process itself made me come across the compaction endless loop

0 0 0 54 0

View Details

Cyan @RoySadaka

3 months ago

@thsottiaux @thsottiaux I noticed that when a session has many images, once the point of compaction reaches, the session is not compacting the images part, only the texts, and you enter re-compaction in every new turn (reproduced it when I made github.com/RoySadaka/casu…)

1 0 1 646 0

View Details

Cyan @RoySadaka

4 months ago

Shipped🚢 another update - screenshot context is now much lighter and faster - small formatting bug located thx to openai.github.io/euphony/ ! #Codex ❤️‍🔥

0 0 0 47 0

View Details

Cyan @RoySadaka

4 months ago

Tibo do you guys ever sleep? Chronicle & order-of-magnitude faster Codex on the way! Feels like Santa is in town 🎁 I've built CCC (Casual-Codex-Completion). Smash the 'c' key 3 times to summon Codex into almost anytext box on macOS. Made with #Codex ❤️‍🔥 github.com/RoySadaka/casu…

Tibo @thsottiaux

4 months ago

We are releasing a *research preview* of Chronicle in Codex. It allows codex to build up memories based on your day to day work on your computer and then refer to these memories to be a lot more helpful. Available for PRO subscriptions and on Mac to start. This is early and

228 147 3K 945K 891

1 0 0 243 0

View Details

Cyan @RoySadaka

5 months ago

My 7 year old son: Dad, what are you playing? Me It's called ARC-AGI-3 Son Cool! can you put it on my Gameboy? (He has RG35XX) Me Hold my beer Any sufficiently advanced technology is indistinguishable from magic #Codex + #GPT54 @OpenAIDevs @arcprize #RG35XX ♫ BloodPixelHero

1 0 3 218 0

View Details

Cyan @RoySadaka

3 years ago

Grateful to #IIEX for this upcoming opportunity ❤️ When AI, HI, and UX come together, market research doesn’t just evolve, it transforms! ✨ Step into this new era with @TolunaCorporate , @gutcheckit & @MetrixLab #ArtificialIntelligence #HumanIntelligence #UserExperience

Toluna @TolunaCorporate

3 years ago

#AI is undoubtedly the hottest topic in the #insightsindustry. And we all have questions. How can it be harnessed? How can it benefit both suppliers and clients? Are there pitfalls? Join us next week at the virtual #IIEXAI event, where leading experts from across the market

0 2 12 874 0

0 1 10 421 0

View Details

Uri Alon @urialon1

3 years ago

📢 Unlimiformer now supports LLama-2! Unlimiformer-LLama-2 allows encoding extremely long inputs without re-training or finetuning LLama-2. This is an initial implementation, but encoding 130k token inputs using LLama-2 takes only a few minutes! github.com/abertsch72/unl… (1/4)

Amanda Bertsch @abertsch72

3 years ago

What if we could run Transformer models without worrying about context length? With our new work Unlimiformer, you can jailbreak your current models to use unlimited length inputs! Preprint: arxiv.org/abs/2305.01625 Thread 🧵 (1/6)

20 157 916 209K 474

3 29 100 39K 58

View Details

Cyan @RoySadaka

3 years ago

Space exploration theme suggested by #ChatGPT Icons brought to life by @midjourney 🎨✍️ Lastly, it's the initial version so expect a bumpy ride 😅

0 0 2 72 0

View Details

Cyan @RoySadaka

3 years ago

(based on humble research) Although much slower than embeddings search, this approach offers higher retrieval accuracy for small scale, up to ~300 docs. Reasoning Based Search is very experimental we expect it to evolve with more research.

1 0 0 52 0

View Details

Cyan @RoySadaka

3 years ago

✨ Venture is live on @pypi 🎉 Powered by @OpenAI's #ChatGPT and @Gradio's UI, Venture is an exploration tool for your projects documentations. github.com/roysadaka/vent…

1 0 3 2K 0

View Details

Uri Alon @urialon1

3 years ago

📢New Paper: Self-Refine: Iterative Refinement with Self-Feedback We use an LLM such as GPT-3.5/4 to: 1. Generate output 2. Provide feedback on its own output 3. Refine its previous output Improves outputs across 7 tasks without additional data/training! arxiv.org/pdf/2303.17651…

4 17 94 11K 17

View Details

Andrej Karpathy @karpathy

4 years ago

🔥 New (1h56m) video lecture: "Let's build GPT: from scratch, in code, spelled out." youtube.com/watch?v=kCc8Fm… We build and train a Transformer following the "Attention Is All You Need" paper in the language modeling setting and end up with the core of nanoGPT.

482 3K 20K 5.3M 10K

View Details

Uri Alon @urialon1

4 years ago

📢 New Paper: Program-aided Language models Prompting methods such as chain-of-thought (@_jasonwei) employ LLM for decomposing the problem into steps *and* solving each step. Instead, PaL decomposes the problem into *programmatic* steps and solves using a Python interpreter. 1/4