I build AI and AI-powered products. My focus areas are healthcare, making SMBs operationally effective and algorithmic trading.
Bangalore
Joined March 2009
- Tweets9.5K
- Following3K
- Followers1.9K
- Likes8.6K
Given @GeminiApp optimized the heck out of it for speed for 3.8 Flash, Argon is extremely slow!
While the output from that is quite good - for many tasks that requires human input - it just lags insanely behind Opus 5.5 and Astra in terms of latency.
100% endorse this.
I still have people saying after 3 months: I am building "x". If that's a standard variety of software product, it shouldn't take that much time at all.
If it is taking you time to ship, you probably are not using agents correctly!
When asked:
"what humans can uniquely do in the AI era"
Peter Thiel goes into a 38 sec pause.
---
If you are the CEO of a two-trillion-dollar AI startup and you go around telling Congress
"please regulate us because our product might kill everyone,"
you are doing two very smart things: asking the government to build a regulatory moat around your business, and telling your employees they work at the most important company in the history of the universe.
--
A very engaging podcast between Thiel and Walter Isaacson.
youtube.com/watch?v=H9Bdv3t5…
This is wonderfully done!
Brilliantly made video explaining the art of chitra-kavya, the art of solving fascinating optimization problems using letters!
Super happy to see my open-source TTS, Vāgdhenu (prathosh.in/vagdhenu/), being used in such magnificent ways. Thanks for creating this, @udbhava.
Success is 99% perspiration. 1 % inspiration.
It is even more true in this day and age of AI agents.
I would add focus also to it. Even sun rays burn only when focused on a particular point.
Everytime a long build is happening in Opus 5.5, I keep asking it "status and eta?".
It gives a darn good picture of the status - with clear challenges and what might take time etc.
But it still is horrible in eta. I've had it give me timelines for 6+ weeks when it finished the entire task overnight.
It has definitely been trained on some terrible real world s/w plans :)
Here's my weekend read/watch list (mostly a watch list)
• What are recursive language models?
• What goes in building a kick-ass software factory?
• The new agent architecture
• How to build an always-on agent?
• A new video series on reasoning models from scratch
Like the city that never sleeps, we now have AI agents that never sleep. They are more commonly referred to as "always-on" agents.
The early wave was openclaw, hermes etc. But that all appealed to the hackers. But with Meta's Muse, Grok's @bot, OpenAI's dot and now Claude's Duet - this has become mainstream and is accessible to everyone.
But what goes on in building this? A great talk by @leerob at Stanford
nitter.cf/leerob/status/21086502…
How do always-on, proactive agents like @Bot work?
Watch my lecture at Stanford CS146S:
2:35 How we got here
6:13 What changed in the models
10:06 Inside an always-on agent
18:07 The harness
27:26 Context engineering
34:26 Where this is going
Following up on his fantastic book, @rasbt has created an amazing video series on Reasoning Models from Scratch. Highly recommend writing and executing the code along with watching the series.
nitter.cf/rasbt/status/211432509…
The complete reasoning-from-scratch video series is now up (and linked) here: magazine.sebastianraschka.co…
(Taking a short break but will be back with LLM model and research updates in November!)
I like how Claude can co-ordinate runs across projects and load balance the runs. The orchestrator (Opus 5.5) has a md file that gives the priority of the projects (based on deadline, criticality etc).
It runs all night - picking up tickets and fixing it across projects - and scaling up or down the sub agents so that machine load/temperature/ram usage are manageable.
There is a classifier on haiku that decides which model the sub agent should use. Based on available usage and Tibo's tweets - it will decide whether to go all in on codex sub agents or stick to claude family.
Currently, my machine is my limiting factor!
100% agree to this. In this age of agentic engineering, kid you not - the person working on the code matters a lot more than ever!
Thanks to @inventcures for pointing me to this !
One for the F1 buffs like me from the stables of @collision .
Timing couldn't have been better - Antonelli is on the verge of being crowned the youngest ever F1 champion.
Huge comeback for Mercedes this year. This is going to be a good listen!
youtube.com/watch?v=mFLcqTGp…