@Atmojoarjalojo A new song of yours drops and the process of learning each little nuance from it and the thrill it gives to sing 0.1% like that is what makes life so much better.
[Just wanted to share]
โก Building enterprise agents at Coinbase with LangSmith โก
Coinbase went from zero to production AI agents in six weeks, then cut future build time from 12 weeks to under a week.
Their Enterprise AI Tiger Team built a "paved road" so any team could ship agents the same way they ship code.
What made this work:
โ Code-first graphs with LangGraph & LangChain over low-code tools. Typed interfaces and unit-testable nodes beat prompt engineering for the use cases they wanted to scale.
โ Observability as a requirement. Every tool call and decision gets traced using LangSmith, our agent engineering platform.
โ Auditability by design. Immutable records of data used, reasoning followed, and approvals given.
Result: Two agents in production saving 25+ hours per week. Four more completed. Half a dozen engineers now self-serve on the patterns.
Agents are a software discipline. When you host them properly, make them observable end-to-end, and test what's deterministic, you get speed where it helps and rigor where it matters.
Read more: https://t.co/ellYHHcixY
Humanity has prevailed (for now!)
I'm completely exhausted. I figured, I had 10h of sleep in the last 3 days and I'm barely alive.
I'll post more about the contest when I get some rest.
(To be clear, those are provisional results, but my lead should be big enough)
The test for people who are really happy for you has may be turned into the linkedin comments which are not templates pre-rendered as buttons.
#thoughts#linkedin#Realizations
sometimes watching a skilled person work can give you more understanding then you could ever get by any documentation on earth...
Sometimes the person may be ai.
#Tech#ai#realisations
Before moving from my role at Google to Snowflake I sat down and did a braindump of all the guidelines that I follow (or followed at one point and wanted to reintroduce).
For those interested, here are the ~34 guidelines that made the cut
most foundational concept in deep learning that no one understands is probably the Neural Tangent Kernel (NTK)
this line of work studies neural networks of *infinite width*, which explain a lot about normal finite-width NNs
and there is exactly one Very Good blog post on them:
๐๐๐๐ฆ๐ ๐๐ฐ๐๐ซ๐๐ฌ ๐๐๐๐ ๐๐ง๐ง๐จ๐ฎ๐ง๐๐๐ ||
President #DroupadiMurmu approves the conferment of 139 Padma Awards including 1 duo case (in a duo case, the Award is counted as one) as per the list below.
The list comprises 7 Padma Vibhushan, 19 Padma Bhushan and 113 Padma Shri Awards.
23 of the awardees are women and the list also includes 10 persons from the category of Foreigners/NRI/PIO/OCI and 13 Posthumous awardees.
#PadmaAwards |
@Luvk1412 Companies let people take test from home and then expect no cheating.
Ofcourse there is cheating.
Everyone Cheats in this scenario.
They can send an HR and conduct offline tests.
OAs getting harder and Cheating is getting more massive.
NVIDIA just made Pandas 150x faster with zero code changes.
It is now directly integrated in Google Colab.
All you have to do is:
%load_ext cudf.pandas
import pandas as pd
Their RAPIDS library will automatically know if you're running on GPU or CPU and speed up your processing.
You can try it here: https://t.co/oq7qkVWztY