Pashutan Modaresi retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Pashutan Modaresi retweeted
گوگل AX رو متنباز کرده؛ یک orchestrator برای اجرای Agentها در مقیاس بالا.
ایدهاش شبیه Kubernetes برای Agentهاست؛ با sandbox، مدیریت state، اجرای طولانیمدت و امکان suspend/resume.
github.com/google/ax
Pashutan Modaresi retweeted
Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry.
Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential.
OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose.
@rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think!
Try it out: openworker.com (requires your own API key)
Source code: github.com/andrewyng/openwor…
Pashutan Modaresi retweeted
As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.
A healthy team needs a mix of these, depending on the product:
- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2
Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?
Pashutan Modaresi retweeted
Absolute bombshell. Data reveals someone made a massive 580 MILLION dollar trade on oil exactly 15 minutes BEFORE Donald Trump posted his tweet about pausing the Iran war. Someone on the inside just made a life changing fortune. The corruption is blatant.
Pashutan Modaresi retweeted
Wir wollen @fohlenfutter/@rponline beim Thema Marktwerte künftig mit einem KI-basierten Ansatz arbeiten. Den liefert ein Unternehmen aus Gladbach, das in Sichtweite des Borussia-Parks sitzt, mit der Plattform gool.ai. ⤵️
This Post is from an account that no longer exists. Learn more
Pashutan Modaresi retweeted
wiwo.de/finanzen/geldanlage/…
Unser Partner Smavesto steht für die Zukunft im Privat Banking. In der aktuelle Auswertung der Wirtschaftwoche wird Smavesto mit sehr gut bewertet. Wir (GET Capital AG) liefern die Algorithmen und sind für die Allokationsentscheidung verantwortlich.
Pashutan Modaresi retweeted
We will be at next weeks @hannover_messe.
Visit us in hall 6, booth B48 and experience real time data anomaly detection and our much improved Qoactive® platform.
#HannoverMesse #DataScience #Industrie40
Pashutan Modaresi retweeted
Many thanks to everyone who visited us at #Hannovermesse last week. We had a good time talking to you and showing our drum based anomaly detection.
Pashutan Modaresi retweeted
If your job uses many parts of your brain, it’s probably safe from automation.
Pashutan Modaresi retweeted
Videos of the 2017 DL and RL summer schools in Montreal are available. fb.me/3VB7eFwYJ
Pashutan Modaresi retweeted
Happy birthday, Margaret Hamilton! Comic by @LukeKingma profiles the computer science pioneer: mitsha.re/MJnW303k1YC
Pashutan Modaresi retweeted
Neat, the CS231n 2017 lecture videos are now up: youtube.com/playlist?list=PL… I hear that was a lot of work :) great job @jcjohnss and @syeung10!
Pashutan Modaresi retweeted
Why am I annoyed by AI hype? Imagine trying to discuss how medicine may impact society when this is what happens:
xitter.cf/Smerity/status/8922546… – at Sydney, New South Wales
Pashutan Modaresi retweeted
The State of Artificial General Intelligence xitter.cf/CyberMagazineX/status/…
Pashutan Modaresi retweeted
Overview of how #Docker logging works and best practices for use dockr.ly/2heapdr
Pashutan Modaresi retweeted
"The Applications of Probability to Cryptography" by Alan M. Turing
arxiv.org/abs/1505.04714
Pashutan Modaresi retweeted
Using a Neural Network to build a memorial chat robot to a friend passed away, from their text messages. theverge.com/a/luka-artifici…
Pashutan Modaresi retweeted
How to make a racist AI without even trying: blog.conceptnet.io/2017/07/1…
Pashutan Modaresi retweeted
Deep Learning for NLP Best Practices ruder.io/deep-learning-nlp-b…
Excellent guide by @seb_ruder!






























