Triet Pham

Unseen what's been seen, unreasonable what's so reasonable

[Triet Pham @trietphamnm]

Omg it is so cute! 😍 huggingface microduck

[clem 🤗 @ClementDelangue]

someone trained microduck to do somersaults 😭

[Triet Pham @trietphamnm]

If you are tired of reading AI-generated technical specs or plans, this one skill definitely saves you.

[dex @dexhorthy]

https://t.co/L0G15QT1Tv

[Rahul @sairahul1]

https://t.co/4U0aNsoAmo

[Kimi.ai @Kimi_Moonshot]

Meet Kimi K2.6: Advancing Open-Source Coding

🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)

What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on https://t.co/YutVbwktG0 in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: https://t.co/uvoSJKyGCY
-
🔗 API: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/9wWvgIQSS3
🔗 Weights & code: https://t.co/Be0hjs2RTP

[Triet Pham @trietphamnm]

Exactly what i was looking for! Let it do your works when you enjoy the life.

[Noah Zweben @noahzweben]

Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control

Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.

[Elvis @elvissun]

https://t.co/DotZ3V6XhJ

[Elon Musk @elonmusk]

https://t.co/Mg0oHBVoxf

[Triet Pham @trietphamnm]

Beautiful and helpful! https://t.co/gVG8HeJGAu

[Triet Pham @trietphamnm]

Almost everything has doubled in price in last 5 yrs. Food and housing are less affordable for many. You can't imagine paying two-thirds for food in LA compared to GA.

https://t.co/wJvacjQBad

[Browser Use @browser_use]

Turns out… Manus is just another Browser Use wrapper

[Waymo @Waymo]

Auto mode activated: We're beginning our first fully autonomous miles for Waymo employees in Atlanta, building on years of experience and 33M+ miles across SF, PHX, LA, and ATX. Public autonomous rides will come to Atlantans exclusively through @Uber later this year.

[Triet Pham @trietphamnm]

This document is gold for .net developers curious about memory performance, and internal GC machinery.
https://t.co/rD5dUFi73i

[Triet Pham @trietphamnm]

Yeah, Cloudflare is incredible in terms of cost. When you think of hosting a small website with small database and storage, Cloudflare is the only option that won't break your bank.

[Triet Pham @trietphamnm]

Noted the date Devin (code name skynet) comes to the world as the programmer lifetime starts counting down 😅

[Cognition @cognition]

Today we're excited to introduce Devin, the first AI software engineer.

Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork.

Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser.

When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted.

Check out what Devin can do in the thread below.

[LangChain @LangChain]

🦜LangChain x Google

The official Google `generative-ai` repo has a ton of resources for getting started with Gemini

This includes SEVEN different notebooks for using LangChain to orchestrate a Gemini-powered LLM app

Dive into all the goodness: https://t.co/5e4yhjGOvt

[Triet Pham @trietphamnm]

ByteDance is secretly using OpenAI’s tech to build a competitor https://t.co/0PqDGB0BQP via @Verge

[Rowan Cheung @rowancheung]

If leaks are true, OpenAI DevDay could be the biggest AI event of 2023.

The way we use ChatGPT is about to completely change.

Here are all the (unconfirmed) leaks we know so far:

[Jerry Liu @jerryjliu0]

Here are 8 key considerations for building *production-grade* LLM apps over your data (RAG) 💡 (see 🧵):

1️⃣ Chunks used for retrieval shouldn’t necessarily be the same as chunks used for LLM synthesis (@maxrumpf)

2️⃣ Embeddings should live in a different latent space than what you get from raw text, which can contain filler that biases the embeddings. Consider passing a transformed text representation or finetuning. (@maxrumpf)

3️⃣ If retrieval isn’t returning the right context, you may need to dynamically load/update the data itself (@maxrumpf, @bobvanluijt)

4️⃣ Design your pipeline for scalability. Latency times in prototyping do not translate to production workloads. Start with easy-to-use, high latency modules but aggressively try to shrink latency component by component (@bobvanluijt)

5️⃣ Store data in a hierarchical fashion: summaries of documents and chunks for each document (@bobvanluijt)

6️⃣ Robust data pipelines in prod don't matter as much if you only load the data once. But they are especially important when the source data is constantly changing (@tuanacelik, @maxrumpf)

7️⃣ RAG isn’t just question-answering: for summaries, you may need ALL chunks, for question-answering, you may need specific chunks. Your chunk sizes may differ depending on the use case (@tuanacelik)

8️⃣ Embedding-based retrieval does not work well for entity lookup. Hybrid search combines benefits of keyword lookup with additional context (@tuanacelik)

All of these insights and more can be found in our fantastic “Make RAG Production-Ready” webinar, now available for viewing on YouTube! 🔥👇

HUGE shoutout to @tuanacelik, @maxrumpf, and @bobvanluijt for a fantastic discussion. It’s clear that we’ve barely scratched the surface - we’ll definitely be doing a part 2!

https://t.co/radWINvFZi

[Architecture Notes @arcnotes]

Database Sharding Explained https://t.co/TPkdXNRGCV

[David Fowler @davidfowl]

.NET 8 is going to be a bombshell of a release 🔥. There are a TON of improvements but one of the things I'm most excited about is better out of the box metrics for our http and networking stack. We're also looing to ship grafana default dashboards #dotnet