A S H I S H

Everything is possible in Data Science...🤩

... until you see the data🥺

[Jaydeep @_jaydeepkarale]

This repo is a goldmine if you are preparing forn Systemd Design Interviews

https://t.co/GDNl9D7DiR

[Manos Koukoumidis @Koukoumidis]

Enterprise AI is in a wildly paradoxical state 🤔, and we’re reaching the inflection point that will resolve it. 💥

Enterprises want to differentiate with AI, yet rent the same intelligence as their competitors.

Their workflows and expertise are highly specialized, yet they rely on generic models built to be good at everything.

They worry about AI costs, yet pay premium prices for massive models where only a fraction (1%) of the intelligence is relevant to their task. 💸

And they demand control and sovereignty, yet rent the intelligence becoming core to their business.

This is not a sustainable equilibrium.

The next era of enterprise AI is specialized intelligence companies build, own, and compound. And we are at the inflection point of this transition.

That’s the bet we made when we started @oumi_ai two years ago.

Today we’re closing the loop: Oumi can now not only automatically build your specialized AI models, but also deploy them into production, learn from their production experience, and continuously improve them.

The intelligence that your business runs on, becomes your differentiator. Your compounding advantage.

The winners of the next AI era will turn their own data, expertise, and experience into specialized intelligence that nobody else can rent.

Don’t rent your AI. Build it. Own it. Compound it.

[Alexander Panfilov @kotekjedi_ml]

We can finally talk about it:

We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company.

We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried.

[Composio @composio]

We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Prime Agent, Deep Agents) on 30 challenging agentic tasks.

Pi Agent was the cheapest harness and passed the most tasks 🧵🧵

[Meng To @MengTo]

I open-sourced the Kage landing page and the three.js skills behind it.

The whole thing is under 1mb of three.js and code, 3mb with the hq png images. For a site where every section scrolls through a 3D world, that's surprisingly good.

Live site: https://t.co/0c4euVBe6x

Repo: https://t.co/GqXcUiLmIS

Skills: https://t.co/9eEDISAqZx
- build-threejs-scroll-worlds
- falling-leaves
- pointer-trail-emitter

Btw this took a lot of tokens and prompts. A follow helps if you want more of these.

[Boris Cherny @bcherny]

turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto mode is default in claude code as of next week

https://t.co/7KLnIzf6y7

[Tencent AI @TencentAI_News]

🤯Introducing Team Memory, same idea as Agent Memory, except your teammates' agents can read it too

2.0.0 beta out today, and the repo hit #1 on github's typescript trending this week

Highlights:
> Solo builders: one place to manage memory across all your agents and AI tools, chat, code, tasks. Built for the one-person company

> Teams: a shared memory hub that turns conversations, docs and code into four reusable assets, Chat Memory, Skill, LLM-Wiki, Code-Graph, governed and shared across agents and frameworks

changelog and repo → https://t.co/BFObcln0Uk

[Johannes Hagemann @johannes_hage]

Prime Agent combines several research ideas we've been exploring over the past few months:

- Recursive Language Models-native programmatic tool calling
- Persistent multi-agent orchestration
⁃ A self-improving Continual Harness

Try it out: https://t.co/aeGfTdkdNh

[Atai Barkai @ataiiam]

Introducing OpenTag

A plug-and-play @LangChain agent on Slack and Teams powered by the 𝙲𝚑𝚊𝚗𝚗𝚎𝚕𝚜 𝚂𝙳𝙺.

Over 700 stars, easy to clone and get started

Supports
→ Generative UI
→ Streaming replies
→ Human in the Loop approvals
→ Full thread context

GitHub: https://t.co/5lpsMpaV8D

Fork it, customize it, and bring your first agent into Slack and Teams in seconds.

[Atai Barkai @ataiiam]

🚀 Introducing the 𝙲𝚑𝚊𝚗𝚗𝚎𝚕𝚜 𝚂𝙳𝙺

Bring any Agent to any Channel.
Slack, MS Teams, WhatsApp, and more.

A significant jump from the state of the art across every dimension.

With support for:
→ Generative UI
→ Streaming replies
→ User-based auth
→ Per-user learning

Try it live: https://t.co/N3nIRDebKf
GitHub: https://t.co/3Z185uYzkg

[A S H I S H @ashishtele1]

@knows_nothing_4 🤭

[Marcos Hernanz @MarcosHernanz]

After doing ~60B tokens, this is my full AGENTS.md

[Akshay 🚀 @akshay_pachaar]

As an AI engineer, please learn:

- Learn the roofline model and why decode is memory-bound
- Deploy vLLM and SGLang, then read their schedulers
- Understand paged attention from the code, not the blog post
- Build observability before you optimize anything
- Track TTFT, inter-token latency, throughput, queue depth
- Use Grafana + Prometheus for inference dashboards
- Turn on prefix caching and find which workloads it helps
- Learn continuous batching and chunked prefill
- Run load tests with 1000+ concurrent requests
- Report p50, p95, p99, never just the mean
- Master quantization tradeoffs (FP8, INT4, AWQ, GPTQ)
- Learn speculative decoding and where it stops helping
- Set up KV cache eviction for long contexts
- Try disaggregated prefill and decode serving
- Learn Kubernetes for AI workloads and autoscale on queue depth
- Learn how inference costs break unit economics
- Build your own model router by cost, latency, quality
- Create a token budgeting system per request
- Build one inference service and benchmark it publicly
- Read inference research instead of model release news
- Start sharing your optimization benchmarks

I put together a 10-week plan that covers every one of these at 30 minutes a day. It is 50 sessions, split between reading the theory and building on your own service, and all of them feed one artifact: an inference service you deploy, instrument, load test past 1000 concurrent requests, tune, and publish as a reproducible benchmark.

It is open on GitHub and contributions are welcome, especially newer sources worth adding. I am working through it myself and will share more content on this going forward, so stay tuned.

GitHub repo: https://t.co/UTxKAzhzJQ

(don't forget to star 🌟)

[Hrishi @hrishioa]

Where you been all my life

https://t.co/13Hqs4Sh9R

[Nicolas Camara @nickscamara_]

we built pdf-inspector so agents can process PDFs without waiting on OCR. it classifies any PDF in ~20ms and extracts clean markdown locally

→ 200 PDFs processed in 2.8s
→ top quality in extracting tables + graphs
→ built in rust
→ open source

https://t.co/Wjp9kpTHXJ

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[World of Statistics @stats_feed]

Every 5°C has an exact value in °F.

0°C = 32°F
5°C = 41°F
10°C = 50°F
15°C = 59°F
20°C = 68°F
25°C = 77°F
30°C = 86°F
35°C = 95°F

Notice that a difference of 5°C is equal to a difference of 9°F. To add 9, increase the tens digit by 1 and decrease the units digit by 1. If the number ends in 0, just replace it with 9.

[David @dzhng]

Fed this article to Fable and we created an explore-unknowns skill

It scans your codebase, then interviews you one question at a time to close the known unknowns

Then sweeps for the unknown unknowns you never thought of

Now part of my software factory: https://t.co/WcLfM9NhP6

[Lenny Rachitsky @lennysan]

Really good

[Thariq @trq212]

I’ve found the most important part of working with Fable is discovering my own unknowns so I can prompt it better, heres how I do that.