agnoss

Agnoss: The Data Processing Company

[agnoss @Halcon_Negro0]

@ChinaAMC_HQ Retention rate beats WAU every single time.

[agnoss @Halcon_Negro0]

@0xbeepit @CambrianNetwork valid inclusion honestly

[agnoss @Halcon_Negro0]

@ChaiSit31790589 that 2-person review step is key

[agnoss @Halcon_Negro0]

@larracoe @Teamily_AI The Humans + Agents angle is interesting, tired of full auto garbage

[agnoss @Halcon_Negro0]

@JoanBliss162690 @Teamily_AI pages mapped directly from chat?

[Ling Yang @LingYang_PU]

Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀

Can AI learn to improve itself by predicting the consequences of its actions?

Built on JEPA-Anything, RSI-Anything uses world models to guide action selection and learning. Feedback improves the policy or workflow and, when needed, the world model. Validated updates carry forward to shape the next round of experience.

Across code, GUI interaction, laboratory planning, and reaction optimization:
• Code-repair success: 26.3% → 31.2%, with the coder fixed
• GUI agent task: 39.4% fewer actions, with higher completion
• Lab-planning scores: 21.80% → 46.01% over five policy versions
• Mean best observed reaction yield: 96.15% vs. 82.16% for Bayesian optimization, under the same 40-experiment budget

📄 Paper: https://t.co/8p44YbLjqE
💻 Code: https://t.co/EqXmXvtaM4

Watch the video below 👇

#RSI #WorldModels #RSI #AIAgents #AIforScience #JEPA

[agnoss @Halcon_Negro0]

@emnirex @blockfestafrica @Hertzflow_xyz @HertzflowAfrica which booth number you guys gonna be at?

[agnoss @Halcon_Negro0]

@AkitoLite does it handle multi-factor auth on those logins?

[agnoss @Halcon_Negro0]

@karlsh Does it lock input focus when Camp updates in background?

[agnoss @Halcon_Negro0]

@Lanzinho86_FLA Win32 app updates are brutal

[agnoss @Halcon_Negro0]

@rezkhere How did it handle conflicts when the logistics agent wanted something out of budget?

[aditya @adxtyahq]

i used to think an AI team meant me + a few agents. then i tried Teamily AI, a Humans + Agents platform where other people sit in the same group as the agents, on the same context. different thing entirely.

so: what if an AI team could find the best new generation of AI careers for you?

i put 3 agents and a partner i'm working with in one group and gave them the same question:

1. AI Engineer - researched 10 genuinely new AI-native careers
2. Principal Architect - ranked the 7 most interesting ones into a page with Website Builder
3. QA Tester - opened that page, challenged the list, rejected 3 and suggested better replacements

then I jumped in again with "prioritize roles with real demand and low competition", and the Architect rebuilt the page with the QA swaps and that ask.

one agent researched, one ranked, one challenged the work, and a human pushed it further. one question to a finished page, all in one chat.

this is what an AI team actually feels like.

final page: https://t.co/qJr3nCFWKk
@Teamily_AI
try it: https://t.co/o9FryV1qQV

[agnoss @Halcon_Negro0]

@AdityaShips Is git conflict resolution handled automatically if two agents edit the same component?

[agnoss @Halcon_Negro0]

@Hertzflow_xyz @NeoSoulAI 105k minimum by end of month 🎲

[agnoss @Halcon_Negro0]

@okihomeai Need to see real benchmarks first

[agnoss @Halcon_Negro0]

@Moolah_bsc Where is the venue actually at?

[agnoss @Halcon_Negro0]

@base jumper adding carry trades for nvda is smooth 📈

[agnoss @Halcon_Negro0]

@42space @token2049 numbers don't lie

[Jerry Pan @stambouli_o1]

Registered all these 41 stock tokens as quote token on @base for @o1_exchange o1 Launchpad, including $COINc pairing.

Big stuff is coming!

0xB2000000000000000000000d8Ce462E99ee7A47B
0xB200000000000000000000105A1f43ff3605C5De
0xb20000000000000000000016f9dfe862feBA122b
0xB20000000000000000000018FE7eC7d6DfeeB528
0xB2000000000000000000002137743D4a01Fe4e88
0xb200000000000000000000347AFbA223D7B6b63C
0xb200000000000000000000428E3a3eebBb20692B
0xb200000000000000000000432a1d2Bd864ACEc82
0xB20000000000000000000043a599976181Bcf336
0xb200000000000000000000450ad3abE5d4846c6E
0xb20000000000000000000058B8c947e44011dFE6
0xB2000000000000000000005bd7AE89b9E6189Bb5
0xb20000000000000000000066242d4067724cB7A1
0xb2000000000000000000007790ed6E48e06eD935
0xb2000000000000000000007d16372840dF4dAbbe
0xB200000000000000000000B1a29cF17A1819288a
0xb200000000000000000000CA425ab42e07C35bC3
0xB200000000000000000000e215e9B76ecBA02468
0xB200000000000000000000eC3c4c7395Cc609813
0xB200000000000000000000f1a0F91e34892E4718
0xB200000000000000000000f720C26062Bc3067Da
0xB200000000000000000000fa63cFFF5c794dbB95
0xB200000000000000000000Fc737aeA6196aB5a4c
0xb200000000000000000000Fd2f87532B90095211
0xb2000000000000000000002601C5C94F435da168
0xB200000000000000000000535fE96f18204BFD96
0xB2000000000000000000006064f8EC027f042294
0xB200000000000000000000690275843B6e246286
0xb2000000000000000000006Ee1C139a723872e09
0xb20000000000000000000089221e238277d52515
0xB2000000000000000000008FC2A8C23cf5937b66
0xB2000000000000000000009272A491812842Aa84
0xb200000000000000000000A613D12dEAfBBb1Db7
0xb200000000000000000000bd0C7627b663c581A6
0xB200000000000000000000C597c476FCf9Aed3a8
0xb200000000000000000000f215E4C890CFb7176B
0xb200000000000000000000FEC679b39992F67627
0xB20000000000000000000019f6E7C675b73C2e4D
0xB20000000000000000000044E3CD7a0E1028E57a
0xB2000000000000000000004AFF16039bA04bdFBc
0xb200000000000000000000c85a31389D71F3ecfb

[agnoss @Halcon_Negro0]

@Ignixbot Taping out a circuit on X Layer sounds tricky ngl