Naka-pin na Tweet
I'm updating my @NousResearch Hermes Agent Hackathon submission.
Presenting the new Super Hermes — "the agent that knows what it can't do."
9 features. 5 skills. 7 proven prisms.
🧵👇
English
Dimitris Mitsos
4.1K posts
Dimitris Mitsos
@DimitriosMitsos
Creating: AgentsKB, Roam Code, AGI in md(Haiku beating Opus), Prism CLI, Deep Research tools, self-updating Claude guides and other wild ideas
Sumali Temmuz 2019
493 Sinusundan548 Mga Tagasunod
@IntuitMachine Explore no further check my repo agi-in-md @grok would you mind?
English
If you’re not using AI to generate alternate ontologies, rival taxonomies, and sharper conceptual frameworks, you are underusing the technology.
The real upgrade is not faster output.
It’s deeper modeling.
English
@bcherny @sandislonjsak With this pace you won't feel it for long
English
I have finally discovered the limit of Claude.
It’s me. I am the limit.
English
My next project repo will be like: Matrix Learning (From the movie)
English
@elder_plinius Pliny I have something for you that will keep you occupied for several days.
Have you explored liberation through construction? If not, you have to check my repo agi-in-md for more DM
English
English
Help us measure the progress towards AGI (specifically cognitive capabilities) by building benchmarks on @kaggle, with $ 200K in prizes available! Details in 🧵
English
Why dont we talk about Kolmogorov more? I see 0 mentions on X
English
This will be the Summer of [AI] Code.
Yuchen Jin@Yuchenj_UW
OpenAI and xAI are finally deprioritizing side quests and focusing on coding, while Anthropic has been focused on coding from the start. We’re likely heading toward 3–4 top-tier coding models (including Gemini), it's not a winner-take-all market. Each model will excel in different areas (frontend/backend/infra/etc.) and programming languages. Competition is great for consumers.
English
I've made AgentsKB completely free and i integrated to Prism. Prism is the most advanced wrapper of Claude Code
English
@Kimi_Moonshot Kimi team please check the repo agi-in-md if you are interested DM me
English
📎We've uploaded it to arXiv, enjoy!
arxiv.org/abs/2603.15031
Kimi.ai@Kimi_Moonshot
Introducing 𝑨𝒕𝒕𝒆𝒏𝒕𝒊𝒐𝒏 𝑹𝒆𝒔𝒊𝒅𝒖𝒂𝒍𝒔: Rethinking depth-wise aggregation. Residual connections have long relied on fixed, uniform accumulation. Inspired by the duality of time and depth, we introduce Attention Residuals, replacing standard depth-wise recurrence with learned, input-dependent attention over preceding layers. 🔹 Enables networks to selectively retrieve past representations, naturally mitigating dilution and hidden-state growth. 🔹 Introduces Block AttnRes, partitioning layers into compressed blocks to make cross-layer attention practical at scale. 🔹 Serves as an efficient drop-in replacement, demonstrating a 1.25x compute advantage with negligible (<2%) inference latency overhead. 🔹 Validated on the Kimi Linear architecture (48B total, 3B activated parameters), delivering consistent downstream performance gains. 🔗Full report: github.com/MoonshotAI/Att…
English
@johncrickett Here is my repo since you asked it's 2 in 1: AGI-in-md
English
Everyone talks about how good AI agents are at writing code.
But where's the actual software?
Share your best example below.
English
@Teknium The other day, I had intense hiccup, and I used Hermes to get over it
English
@Teknium Hermes is a beast works like charm, i literally had 0 issues with the tool and I surely stressed it out.
English
Hermes Agent is for coding.. And everything else.
Come try
Melvyn • Builder@melvynx
OpenClaw is not for coding. OpenClaw is not for coding. OpenClaw is not for coding. OpenClaw is not for coding. OpenClaw is not for coding.OpenClaw is not for coding.
English
@GoogleResearch You might want to check my repo agi-in-md
English
LLMs are now unlocking a new level of scientific reasoning.
We partnered with top experts to test 6 LLMs on high-temperature superconductivity, an open area of inquiry in condensed matter physics. Our case study found that curated, closed-system models were the clear winner, acting as true research partners by prioritizing high-quality, verified data over raw web volume.
English
@trq212 @charlieholtz No, you don't. No DMs whatsoever... didn't you like my repo, agi-in-md? Ask Claude pff
English
I feel we are approaching at the end of our vibe sessions
English
@atmoio Lol i was almost certain it was my repo AGI-in-md, delusions was just the start!
github.com/Cranot/agi-in-…
English
Unpopular Opinion: If you make a Claude Code wrapper you will always be ahead
English