0xd9c

[Deli Chen @victor207755822]

🧵 Deli AutoResearch SKILL is now officially open source! 🎉
https://t.co/V3lwwdyQm8

Alongside it, we’re dropping our 4th survey paper — this time on Self-play.
https://t.co/SEb2qoKCI6

Inspired by AlphaZero, we got a powerful insight: prior knowledge doesn’t always lift the ceiling.
Models can discover more globally optimal solutions just by playing against themselves.

The biggest change in this paper?
For the first time, the AutoResearch Agent autonomously planned GPU experiments — and submitted actual RL runs on the DeepSeek 285B model.

The entire RL pipeline — experiment design, code writing, running, debugging, and conclusion summarization — was 100% automated, with zero human intervention from me.
This was incredibly difficult, but an incredibly important step.
https://t.co/kuZZNux5RH

GRPO is the tool being called by the AutoResearch Agent here.
We see this as the beginning of our Continual Learning research journey. 🚀

As always, this is my personal research project, unaffiliated with any organization. All views are my own.

#AI #ReinforcementLearning #SelfPlay #OpenSource #AutoML #ContinualLearning #DeepSeek

[0xd9c @0xd9c]

@SuperSecretRare We're still here🔥

[0xd9c @0xd9c]

@Rosentica @solana 🔥The One Arena

[CJ Zafir @cjzafir]

Codex can get dumber and slower on long sessions.

Here's the fix:

1. Run Process_narration=false

This will stop Codex from showing you all the planning steps, resulting in saving a lot of output tokens.

2. Prompt: "Act as an orchestrator. Use parallel agents to do the research and execution work. Write detailed tasks for each parallel agent and force them to act, iterate, get their tasks done, and bring back an in-depth report. Your job is to deeply analyze the agents' work, provide feedback, and provide them with continuous tasks."

This prompt offloads the majority of the context-burning work to agents, and each agent has its own context window. So you can utilize 5 agents (5 context windows).

3. Add this hard rule: "Measure twice, cut once policy."

Debugging and patching is messy work. Force Codex to plan first, act after (don't use plan mode; it's just overcomplicated). Ask it to make a task list for every task so it can track progress and iterate better.

4. Add this hard rule: "Keep the codebase clean, no tmp files, no dead code, no dead files. Stay organized all the time. No unnecessary folders, subfolders, or files."

Claude keeps most of its working files in cache as temporary files (which is bloatware, but it keeps the codebase neat), but Codex is output-heavy. It creates tons of folders and files, and your workspace can become a mess after a few sessions. As a result, this contaminates the context window and degrades performance. Force Codex to stay organized and follow the file structure.

These 4 techniques can help you save 40% context every session, and performance will be a lot better.

For planning, use Codex 5.5 (extra high), and after the plan is done, shift to Codex 5.5 (high) with fast mode. This works faster.

[CJ Zafir @cjzafir]

Codex 5.5 hack:

"Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy"

This works like charm. It makes Codex 5.5 high perform even better than codex 5.5 extra high.

Why? Codex 5.5 is the only model i noticed that is self aware. It never makes high claims unless the model verifies everything.

This doesn't work with Opus 4.7 cuz that's a very insecure model. You can paste this prompt over and over again, the model keeps saying "you're absolutely right,....."

But with codex, after 2-3 iterations you'll notice yourself it actually patched all loopholes and this genuinely sounds like a good strategy.

Try this out, thanks me later.

[0xd9c @0xd9c]

@Rosentica I think you forgot to send me the code

[0xd9c @0xd9c]

@Rosentica Can’t wait enter One Arena world🔥🔥🔥

[0xd9c @0xd9c]

Just pulled a COMMON KENJI badge from registering the waitlist for One Arena @Rosentica!

Can't wait to battle and win more grails with my RWA cards!

See you in the Arena ⚜️
#OneArena #Rosentica
https://t.co/10EzYWZcx8

[Rosentica: One Arena @Rosentica]

꧁⊹ WAITLIST OPEN ⊹꧂

Bring Your RWA Cards to Battle.
Compete for the Grails.

Collect, Social, Yield.

Test your luck, summon your own hero to join the waitlist:

— https://t.co/xFzgWKcuZl —

*Waitlist and Hero Summon are spot limited on a FCFS basis.

See you in the Arena ⚜️

[Onigiri Freya @ONIGIRI_CATBUS]

- @Rosentica 创始人Natsuki受邀成为@superteam 成员（SOL基金会出资运作的核心Builder圈子）

- 旗下RWA卡牌对战平台 One Arena 四月beta测试，waitlist即将限时开启，打开官号🔔

- 平台收入回购 $ONEP
$CARDS 开启收入回购涨到195M，资金对卡牌赛道无比饥渴

- $ONEP 由 $ONE 和 $FREYA 等价兑换 , 实体背书的合规资产，四月TGE，兑换将于TGE 72小时前关闭（有无提前通知取决于Listing伙伴的公告时间，建议尽早）TGE 48小时前开启领取，详情见官推@Freya_Starfall

卡牌赛道的体量持续疯狂增长，toly和solana的人不断提到，而且目前仅仅停留在“价值存储层”

类似DeFi之于ETH，One Arena创造了链上卡牌的应用层，让卡牌可以在链上用来对战、押注、赢取收益、租借、生息。这是一个完全未开拓的新市场、解锁并定义这个新市场的产品会承接这个市场的爆发和用户+资金流入，成为自身营收和估值增长

而坐拥日本业界资源、卡牌游戏开发背景、深耕加密和IP方向并已完成完整布局和先发优势的R社在推出这个杀手级应用上有着无法追赶的护城河。回看这一路的布局，每一步都不可或缺，IP和实体背书合规升级是重中之重

@solanagaming 官方提到Solana会倾斜大资源来支持链上卡牌游戏，并评论了Natsuki的推文表示欢迎同时关注了官推

卡牌赛道疯狂增长，而且还处于只有底层价值存储机能的早期，想吃到最大的赛道红利，开辟应用层的@Rosentica $ONEP 一定一定要关注。布局 $ONEP 或是蹲守waitlist，目前看只有这两种方式

[0xd9c @0xd9c]

@Rosentica 🔥🔥🔥 can’t wait

[0xd9c @0xd9c]

@TabinekoKIKI @Freya_Starfall Hi Nat, just want to confirm the conversion formula.
Is the amount of $ONEP received calculated based on:
allocated pool % × (holdings/total supply)
Is the final conversion amount determined by my share of that token’s total supply, rather than by token price afterward?

[0xd9c @0xd9c]

@ONIGIRI_CATBUS 真正RWA落地

[0xd9c @0xd9c]

@TabinekoKIKI @cl0udg0d_ @Freya_Starfall @Rosentica @solana @colosseum LETS GO

[0xd9c @0xd9c]

@TabinekoKIKI Can't wait to try

[0xd9c @0xd9c]

@Freya_Starfall Everyone needs to have a dream

Bm24h9yBQRv5C2feeXvUxVgzba1C1cjh6LYRKfTRREG

[Onigiri Freya @ONIGIRI_CATBUS]

Crazy attention on ONE PIECE and it will only grow stronger. Final arc begins from April.

Both $ONE benefit from the attention, one of them has actual IP & royalty inflow & strategic reserve to inject value from ONE PIECE to the token, and the other one is a one-time “news hype” meme.

Quite easy for me to choose which one to invest in to benefit from the ONE PIECE momentum in 2026:

EybU41yD9sAvECDuRuRiDKssf5qBFHzeQgaNWE4rbonk

I mean I don’t see a world where the other one with a icon from the news won’t be trumped by other crazy ONE PIEVE news shortly, and we all know that there’s a lot of them crazy big news coming.

[0xd9c @0xd9c]

@Freya_Starfall Dreams Never Die
ONE PIECE
$ONE

[阿尔法 @alpha101xyz]

Binance前 Listing Manager 亲口说：

"币圈根本没人看长期。
决定价格的只有三件事。"

他两年半看了 1000+ 项目，
去年亲手支持 100 多个 token 上线。
电话会后能成功上Binance成功率 5%-10%。

我作为几个 Binance listing 项目的 advisor，
参与过项目方与币安沟通的电话会。
跟Chase虽不算熟人，但我听过他怎么判断项目。

这次Lizheng (DY:课代表立正）和Chase @ChaseWang
的访谈里的几个启发人的点：
-为什么“泡沫破裂”十年没发生
-BTC 有没有“庄家信号”
-稳定币为什么是核武器
-预测市场=信息资产化
-AI agent 经济为什么必须用 Crypto

我把核心观点 + 我的Research
拆成几张「认知地层图」分享👇

[0xd9c @0xd9c]

@Freya_Starfall GEHbsStGFqm9D6qmfzx5ByPQbbzxKPchqLM6NzX9d1tm

$ONE coin save ur life

[0xd9c @0xd9c]

@bonkfun @Bonkswap_io $FREYA 🤝 $ONE