Ashish
banner
tulsani.net
Ashish
@tulsani.net
Digital, Data, analytics, insights, AI, Agents, LLMs, Memes
tulsani.net
Testing for a post. It's interesting :)
August 14, 2025 at 6:09 PM
Testing persona vectors as described in Anthropic’s latest paper: How to Monitor and control character traits in language models. I ran an experiment with intentional hallucination to see how well trait steering works. AI safety isn’t just theory, it’s hands-on!
August 3, 2025 at 2:35 AM
Testing persona vectors as described in Anthropic’s latest paper: How to Monitor and control character traits in language models. I ran an experiment with intentional hallucination to see how well trait steering works. AI safety isn’t just theory, it’s hands-on!
August 2, 2025 at 4:25 PM
Got an invite to use @PerplexityComet , I will be trying out few interesting things!
July 28, 2025 at 5:00 PM
This is interesting!
July 21, 2025 at 3:19 AM
The notion of causality arises from our discomfort with the unfamiliar and our tendency to seek the familiar in the new.

Predictability comes not from laws or necessity, but from repeated patterns. Regular occurrence does not imply a deterministic cause.
July 20, 2025 at 5:25 PM
Grok introduced me to Mermaid Chart, and I can't stop using it!
July 17, 2025 at 3:30 AM
A brilliant example of applied LLMs in low-resource, high-impact settings.

Dr.Copilot is a multi-agent assistant that helps Romanian doctors improve how they communicate with patients in telemedicine. It focuses only on the quality of the message, not the medical content.
July 16, 2025 at 8:07 PM
I am excited to share that I have successfully completed my 7 hours of sleep today!
July 14, 2025 at 9:23 AM
Fun and Chaos!
July 14, 2025 at 9:22 AM
What people want Copilot to help with (left side, red bars),
What Copilot actually does (right side, blue bars), and
What real workers typically do (black lines on both sides).
July 11, 2025 at 6:45 PM
Search results on arXiv now show phrases embedded in research papers. This looks like prompt injection aimed at LLM based review systems.
If LLMs are being used to summarize or review papers, and authors are injecting prompts to bias the output, the credibility of research analysis is compromised.
July 8, 2025 at 7:47 PM
The joy of running an LLM on a local system is surprisingly rewarding, what’s stopping you?
July 6, 2025 at 6:22 PM
June 30, 2025 at 9:02 PM
January 22, 2025 at 7:31 PM
This feature is the boon for all unsolicited calls in #iOS
January 21, 2025 at 8:33 AM
What has greatness must be spoken of with greatness, cynically and without shame, or not at all.
January 19, 2025 at 10:39 AM
Did not see that coming…
January 11, 2025 at 5:27 AM
For all the research folks, hope this helps!
connectedpapers.com
January 6, 2025 at 5:20 PM
Conversations on the bird app. He seems to be kind and patient
January 5, 2025 at 5:04 PM
January 5, 2025 at 4:56 PM
Post a pic you took with no description to bring zen to the timeline.
January 3, 2025 at 6:41 PM
It seems that #IndiGoAirlines needs to hire few analysts.
January 3, 2025 at 1:41 PM
I still find this funny
January 1, 2025 at 12:36 PM
January 1, 2025 at 3:10 AM