Christian Langreiter

how hard could it be?

[Tom Fuerstner @kevospore]

Expect massive innovation now that anyone can build apps for the S-band! This 2-4 GHz radio frequency sweet spot cuts through bad weather easily, making it perfect for tracking storms, keeping airport radars accurate, and beaming data to space missions.

[Kat ⊷ the Poet Engineer @poetengineer__]

my current favorite learning mode: a book/paper pdf open in claude desktop’s browser pane, where i highlight passages and ask questions straight with claude. alongside it, an implementation of the idea im reading about so i can play with it. immediacy in both ideas + intuition.

[Christian Langreiter @chl]

/inquire

[Nick @nickcammarata]

interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had

with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works

https://t.co/zHij5zwKGT

[Nirmalya Kajuri @Kaju_Nut]

"Our initial evaluation suggested that GPT-6-Astra's score was in the late eighties followed closely by Opus 5.5. But, as we started to investigate the mistakes that the models might have made, the models, especially Astra, insisted that they were right and that it was the expert-supplied answers that were erroneous. When we went back to the experts it turned out, in multiple instances, that that the experts found some subtle errors buried deep inside their calculations. As they revised their answers, Astra's score started to inch up and it finally ended up with 98% (49/50)."

[David @DavidSHolz]

i asked LLMs to have fun, write down what happened, then rate who had the most fun. the newer models seem to have less fun! many models played word games, but opus 4.6 won over and over by imagining brief worlds made up of contradictions living inside falling water droplets 🥺

[Fulcrum @fulcrum_inc]

Echo is post-trained from Kimi K3. Training Echo was so cheap because the underlying base model already has a deep understanding of writing style. All that we needed was to elicit this understanding—taking the model out of the “assistant basin”—while preserving its other capabilities.

[Christian Langreiter @chl]

the age of superidiosyncratic software

[Conrad Barski @lisperati]

spent a couple of hours today on creating a file browser that works exactly how I would want it to work, even if it would drive any other person insane

[darren @darrenangle]

asked claude opus 5.5 to make a film about intelligence arising from text sequences

stupefying that this is all code. what a model

(warning: flashing lights)

[Jack Clark @jackclarkSF]

"stochastic parrot" was a mimetically-fit cognitive virus that spread from 2021-2025; it temporarily blinded many gifted people to the nature of AI progress, burning up crucial years in which they could have helped think through the response to the situation.

[Kat ⊷ the Poet Engineer @poetengineer__]

watching this susan kare (designer of icons/graphics for the original mac) talk and thinking about how accidental constraints can help make the most memorable designs by pressuring toward simplicity.

[Haijun Xia @HaijunXia]

This is the kind of "AI Magic" I love. Not through delegation and instruction, but through direct interaction with intelligent and dynamic materials.

[maharshi @maharshii]

i shed a tear reading this blog post by a deepseek kernel engineer

[Delip Rao @deliprao]

Hypothesis testing is making a huge comeback thanks to coding agents writing papers now. It's everywhere in most submissions I review, including the abstract. Also, I am learning about new hypothesis tests that were never used before in our community (NLP). I don't know what to make of it -- good i guess?

[Christian Langreiter @chl]

https://t.co/UmdbW2uWbA

[nim @eminimnim]

Vibe hardware is here.

I gave Astra my credit card and asked for a Teenage Engineering-style mini DJ controller.

It generated a concept image, sourced parts, read Chinese datasheets, built a CAD model, ordered everything, then made a Blender animation showing how to assemble it.

[Christian Langreiter @chl]

✨

[Christian Langreiter @chl]

https://t.co/WyoLPeAnkD

[thijs @cdngdev]

i gave astra a robot, a paint brush, and a camera then asked it to paint the golden gate bridge in real life!

it figured out how to control the robot, and progressively got better throughout its attempts. the timelapse is sick

[Goodness, how could that do? @Kinch_ahoy]

It always astonishes me how fearless @deepseek_ai are when compared with other labs. *Every single* model release is packed with novel crazy clever ideas, and each is fully commited to with near frontier scale training.

[Sholto Douglas @_sholtodouglas]

put it in a museum

[Christian Langreiter @chl]

@emanperez28 fantastic idea!

[thijs @cdngdev]

i gave astra a robot, a paint brush, and a camera then asked it to paint the golden gate bridge in real life!

it figured out how to control the robot, and progressively got better throughout its attempts. the timelapse is sick