Mehedi Hassan Dipu

Intentionally left blank

[Hanako @hanakoxbt]

Andrej Karpathy (ex-OpenAI, ex-Tesla) just released a prompt that turns Opus 5.5 into a graph that actually finishes any job.

It's f*cking unreal...

send it to Opus 5.5, and thank me later. Then read the article below ↓

[Ishika Rawat @Ishh_021]

Anthropic Engineer: "At Anthropic, we don't write prompts anymore. we build loops"

in 42 minutes, she shows how the Claude team creates loops that prompt themselves

if this cost $400, people would call it the best agents course of the year

it's free

watch it, and Bookmark.

[Zara Zhang @zarazhangrui]

Video essay: how to create tasteful things with AI without being a designer

[Grace Clarke @graceclarke]

This was an insane read.

https://t.co/nhuEwTZrLb

[Sharon Li @SharonYixuanLi]

I know many PhD students are questioning what their paths mean as AI accelerates scientific discovery. That anxiety deserves to be taken seriously.

I wrote some reflections in a recent blog post. My students found them helpful, so I’m sharing them more widely.

I hope it offers a little light as we navigate this strange time. Please share it with someone who might need it.

https://t.co/wr1upnki47

[Ava @noampomsky]

it’s very liberating to realize judgment is mostly a form of self-protection and you can let go of it once you feel safe

[Andrew Akbashev @Andrew_Akbashev]

My new lecture - Who will become a professor? And why?

Three PhD students with three dramatic stories, each with a different career path hoping to stay in academia.

If you want to become a PI, you may face challenges you never anticipated.

It’s easy to make mistakes and be misguided by someone’s advice.

It’s easy to get stuck on ‘infinite postdoc’ or hit a wall as a dual-career academic couple.

In this talk, I show how unpredictable your academic career can be.

I also explain how PhD students often miss out on opportunities.

What should students do to significantly improve their chances? How to compete for academic positions?

Lecture: “The Real Cost of Following Your Academic Dream”

https://t.co/TKAczWuQFg

(I recently gave this talk at the PhD / postdoc symposium in Swiss Alps)

[Akshay 🚀 @akshay_pachaar]

Google just open-sourced Harness².

(turn any harness into a self-improving system)

a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup.

Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched.

on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved.

because it learns from the differences between runs, it needs no correct answer or grader for the task.

that covers a single task. Harness² also carries what it learns from one task into the next.

after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch.

this means every finished task makes the next round of edits more informed.

Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher.

those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work.

you can find the Harness² repo here: https://t.co/i00WLeeFpw

I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand.

that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.

[Dhruv kumar @Dhruvkumar16797]

Andrew Ng just dropped the best 2-hour course on Graph Engineering: from single agent to full automation

9:14 - your first agent
33:11 - loop engineering
1:02:46 - graph engineering
1:30:15 - agents that rewrite themselves
1:49:05 - full graph system

two hours, and it replaces every agent tutorial you bookmarked this year

Prompts → Agents → Loops → Graphs

most people will stop after the first agent and call it automation

he saves the last forty minutes for the graph that runs it without him

same model, same tokens, completely different week

watch it today

[Lunar @LunarResearcher]

Andrej Karpathy:

"Prompting is going away. Delete everything, keep Graph."

In just 69 minutes, he shows how to build graphs and why they're the only layer that survives in the end

Prompts → Agents → Loops → Graphs

a loop keeps one agent running until the job is done

a graph decides which agents exist and what each one passes to the next

anyone can build an agent, almost nobody builds the graph that runs them

watch it today, then save the full guide on graphs below before everyone starts catching up ↓

[Claude @claudeai]

120 handwritten pages, turned into a working font with Opus 5.5.

[Miles Cranmer @MilesCranmer]

Here is the full talk:

[Mathelirium @mathelirium]

In Finite Element Method (FEM) of Computational Electromagnetics, a complex domain is divided into many small elements, and the governing equations are approximated and solved across those pieces.

Here, we demonstrate the method by using a triangular mesh to simulate an electromagnetic wave travelling through a lens.

[fofr @fofrAI]

Argon has this amazing natural understanding of the world. It can do so many things from first principles.

Here's a pelican riding a bike, using fourier epicycles.

Video made by Argon.
Time-synced Lyria 3.5 music prompted by Argon.

[Sadao Tokuyama @tokufxug]

キャリブレーション不要、1枚の画像から道路利用者を3D検出🚗

🔹UrbanOmniDetect-2が1枚の画像から3Dボックス生成
🔹第12世代ノートPCのIntel Iris Xe＋OpenVINOで30fps
🔹最大34台を同時検出、道路を上から見たマップに配置

検証：Luís Condados
モデル開発：Mehmet Kerem Turkcan
情報元はリプ欄。

[Muhammad Rizwan Munawar @muhammdrizwanmr]

Can you turn a regular camera view into a bird’s-eye view? 👀

Using @ultralytics YOLO26 + homography in Python, I built a demo that tracks vehicles and maps their movement onto a top-down view.

Useful for traffic monitoring and movement analysis.

#BirdEyeView #MachineLearning #AI

[lyra @_lyraaaa_]

this is the kind of software that makes ppl generational wealth

[Sabine Hossenfelder @skdh]

Expert predictions about AI progress have been stunningly inaccurate

https://t.co/QYinVEdz2l

[Christian Szegedy @ChrSzegedy]

Reading all those recent beautiful essays by Terry Tao, Kevin Buzzard and @wtgowers, I could not resist, but write up my deeply personal perspective on how I perceive and see things:

https://t.co/fvWb4b7jGU

[Paul Graham @paulg]

"Do not bet against the airplane. The skeptics who say AI can't conjecture, can't theorize, and can't explain are describing last spring's models. Within months, they will be describing nobody. The evidence is already on the table, and those with eyes can see it."