Daniel Mondragon

Code, build, lift, repeat.

[Acyn @Acyn]

Wright: 121 years ago, Albert Einstein published a paper—

Trump: Nobody cares.

[Riley Brown @rileybrown]

If I had a budget of $10,000 to build a local setup to run GLM 5.2 locally AND any future local model that comes out soon what should my computer set up be?

[Ben Dicken @BenjDicken]

Remember that time @brendangregg shouted at hard drives to make them slower?

Someone please confirm nvme ssd is immune.

[Agencia de Transformación Digital @AgenciaGobMX]

📣 Especialízate y certifícate en Análisis de Datos.

👉🏽 Inscríbete en la segunda convocatoria nacional para estudiar en el Centro Público de Formación en Inteligencia Artificial

✅ 100% GRATUITO
✅ Completamente en línea
✅ Acompañamiento de expertos en tecnología
✅ Inglés complementario

Regístrate antes del 5 de julio en🔗 https://t.co/SrPuE97zYQ

[Ali Yahya @alive_]

i still think about this

specialization is for insects

[𐙚⋆ @voidwithverses]

“An enemy will agree, but a friend will argue”

— Russian Proverb

[Peyman Milanfar @docmilanfar]

I regret to inform you that “working” from a cafe is a myth. same for “studying”

[zack @zack_overflow]

Why does tsgo use so much memory?

Because it literally never frees memory allocated for types!

And multi-threading overhead makes it likely to duplicate typechecking state on multiple threads

I wrote about this in more detail here: https://t.co/7od2GMrVAW

Basically:
- nearly every type is allocated and then never freed (including transient types which are created and destroyed very quickly)
- each thread gets its own type-checking state (types, symbols, etc.)
- but they don't share data
- so it's very easy for one thread to end up recomputing and allocating memory for types/symbols/etc. that another thread already did

The end result is a very high peak memory usage!

[Charlotte Lee @cljack]

before you waste a lot of time in therapy trying to understand men, consider that Napoleon got volunteers to man a battery position with an almost 100% casualty rate by simply renaming it "the battery of not being a little bitch"

[xAI @xai]

You can now use your @grok or X Premium subscription in @opencode.

Use the model powering Grok Build for high speed and codebase intelligence.

https://t.co/8D2F9jYoIQ

[Brotzky @brotzky]

Introducing https://t.co/ycxJEf1z7w!

A new space where I explore how the best apps in the world are built.

First piece:
How's Linear is so fast? a technical breakdown.

https://t.co/9Vu1syrn1i

[dax @thdxr]

branded types for absolute vs relative paths are gonna save my life

[Daniel Mondragon @mondra_dev]

I'll take a look in 10 years

[Daniel A. Saedi (DataManDan) @TheRealDanSaedi]

The singular red dot is causing a massive compute shortage and you think memory stocks have topped?

[Daniel Mondragon @mondra_dev]

@vponamariov @threadreaderapp unroll

[BROONO ㊆ @BROONOart]

I like goin to the gym at 3pm bc it’s just all the people with mysterious income sources

[a16z @a16z]

Scrolling is on the decline

More charts: https://t.co/2IoX6EtHav

[dax @thdxr]

here's a chart showing them being a few months behind and catching up

modern day is amazing you can have whatever narrative you want!

[Rodrigo Hidalgo @rod_hidalgo]

En 1869, el calor era un motivo para viajar a Tacubaya, a San Ángel y a los pueblos donde había “sombra y frescura”: https://t.co/dLaBVanXsd

[Daniel Mondragon @mondra_dev]

@juandadotdev at this rythm you could start to use vim in 3 years aprox 😂

[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