Myrha Khan

brango

[Myrha Khan @apple2eth]

@monad_xyz 0x2B8bB5f7e8f776E9ce22127cfCDeE74Dd47de82B

[Myrha Khan @apple2eth]

@SurferSkullz BSStkCBguPjbWAE1czWa8vJNoaC3ahwaxQGjEccsVVZ1

[Myrha Khan @apple2eth]

#MindNetworkTestnet #FHE https://t.co/JLd2X4kNM5

[Mind Network @mindnetwork_xyz]

📢 The Mind Network #FHE Testnet Episode 2 campaign is now available on @Galxe: https://t.co/GW1ZXLkClQ

Embark on the #MindNetwork Odyssey journey where tasks revolve around engaging with other top crypto projects. More are coming soon!

You're always welcome to try out our testnet anytime: https://t.co/fMyBoHgaXN

[Mind Network @mindnetwork_xyz]

📢 Exciting news!

We are thrilled to announce the successful completion of our seed round fundraising. Huge thanks to our incredible investors! Together, we're ready to revolutionize the future of Data Privacy! #MindNetwork #ZeroTrust

Dive in: https://t.co/49MJ5Vfe1J

[Myrha Khan @apple2eth]

@100trillionUSD @gaga_node next bitcoin! open gift box. LFG !!!

[Myrha Khan @apple2eth]

@MMCrypto @gaga_node next bitcoin get free airdrop.LFG!!!

[Myrha Khan @apple2eth]

Calling all crypto enthusiasts!⛏

Supporting the blockchain evolution by signing up #GaGaNode to mine and earn 🌐

Starting today, use my referral link 🚀: https://t.co/OXxHI6hynj

[meson.network @NetworkMeson]

🚀 Exciting News! Meson has just landed on the Goerli Testnet! 🌐✨

Join us in exploring $Meson and testing its capabilities on GoerliETH at https://t.co/1vpCWZ0gmf and https://t.co/kQkqvrjhgg.

Let's shape the future together! 🚀

[elvis @omarsar0]

Principled Instructions for LLMs

Nice set of guiding principles to improve and enhance the quality and reliability of LLM responses.

Shows the effectiveness of the principled instructions and prompt designs across model sizes and scenarios.

Tested on Llama 1/2 (7B, 13B, and 70B) and GPT-3.5/4. (see examples in the figure)

It's well known that prompt optimization can lead to significant performance gains. If you are building or researching with LLMs, this is a great read.

https://t.co/4c4VBI6llk

[Myrha Khan @apple2eth]

https://t.co/f5bJKyooJf @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @sociapol in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/ApcBpGTNpV

#Web3 #Chosen #SPOL

[Myrha Khan @apple2eth]

https://t.co/zsVr6PflXj @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @FarcanaOfficial in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/ADJOaYqgJS

#Web3 #Chosen #FAR

[Myrha Khan @apple2eth]

https://t.co/VYhNqhOaHN @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @RainmakerGaming in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/O1BBcI8MU4

#Web3 #Chosen

[Myrha Khan @apple2eth]

https://t.co/ZTsrpshbbO

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @RealBobaFinance in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/d1gLFfuAJ6

#Web3 #Chosen #BobaFinance

[Myrha Khan @apple2eth]

https://t.co/ViLFHtRQgU @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @Digiversede in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/LA7ncHSPGq

#Web3 #Chosen #Digiverse

[Myrha Khan @apple2eth]

https://t.co/oJzf6BmdPa @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @stratumexchange in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/quAhwTRO3e

#Web3 #Chosen #strat

[Myrha Khan @apple2eth]

https://t.co/6dGofeWCrN @argentHQ
@TrustWallet
@syncswap

[CHOSEN ∞ @ProjectChosen]

Another new 𝐏𝐫𝐢𝐜𝐞 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐏𝐨𝐨𝐥 for @Port3Network in the realm of #IDO/#IEO, has been launched by 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐂𝐡𝐨𝐬𝐞𝐧.

🚀Visit https://t.co/xg3aULIR3M, switch to @zksync & join for rewards!

https://t.co/V4cXzSdcxX

#Web3 #Chosen #Port3

[Socrates @Socrates_global]

🎆Our special New Year's gift of 10,000 USDT is coming again!

The second 2,000 USDT gift is ready to be given on #Galxe

Join now: https://t.co/xjZgSD2fba

[Myrha Khan @apple2eth]

Just reached 1506 on Pinkdrop 🎀! Compete with us via @pinkonomic

[elvis @omarsar0]

Self-Improvement for Multi-Step Reasoning LLM Agent

Proposes a ReAct-style agent with self-critique for improving on the task of long-form question answering.

It shows that the agent can be improved through ReST-style (reinforced self-training) iterative fine-tuning on its reasoning traces. Specifically, it uses growing-batch RL with AI feedback for continuous self-improvement and self-distillation.

Like a few other recent papers, it focuses on minimizing human involvement (i.e., doesn't rely on human-labeled training data). It generates synthetic data with self-improvement from AI feedback which can then be used to distill the agent into smaller models (1/2 orders magnitude) with comparable performance as the pre-trained agent.

Great paper with interesting ideas of how future LLM agents could be improved and how to deal with challenges like obtaining multi-step human-labeled data at scale.

https://t.co/OAHXDMyOXR

[Tanishq Mathew Abraham, Ph.D. @iScienceLuvr]

Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models

abs: https://t.co/TxemYtTgCi
code: https://t.co/Yqw59smmPH

The authors observe that during sampling the U-net encoder features do not change as much as the decoder features. Based on this, the authors introduce "encoder propagation" to speed up diffusion model sampling.