making hamster mazes for LLMs. resident nixpert @NousResearch
Joined November 2019
- Tweets 2,051
- Following 800
- Followers 4,987
- Likes 3,858
306 Photos and videos
Jun 13
Table for one: How Nishi turned dining alone into a movement
On June 9, 31-year-old Nishi Singh hosted the first offline gathering called Table for One Club at Hauz Khas’s Fort City
Read the details here ➡️
hindustantimes.com/cities/de…
(✍️@somyalakhani)
🗞️ For in-depth reporting:
epaper.hindustantimes.com
📩 Subscribe now: bit.ly/2QAOH22
1
1
13
1,541
We’re excited to welcome @sidbing from @NousResearch this Saturday to share insights into the latest Hermes Agent research and what’s coming next!
We're hosting a Vibe with Hermes Agent mini workshop and build-along this weekend with @savantnimit.
Bring a real problem, explore how Hermes Agent can help, build your own workflow, and leave with something practical to keep improving.
📍 @2586Labs
📅 13th June
Apply now 👇
2
6
49
12,132
cmux didn't stick for me. ig i gotta try this one out.
May 31
herdr.dev is a fantastic piece of software.
I was in the early stages of building something similar, but happy to throw it away cuz this is *so* much better.
1
802
ingest and read everything you need to know, docs, code etc.
step away from ur 'puter, sit with a pen and paper and write stuff down until feels complete.
when facing ambiguity, ask the agent/read some more and step away again.
until what you have on the paper feels solid.
then wispr flow into an agent and ask it to keep asking u questions until it's also on the same page.
then hit /goal with the spec.md and step away
May 23
Stepping away from the dopamine chat box and recording a long, rambling, yet intentional voice memo covering everything you want to accomplish in whatever project you’re working on. Then transcribing that and using it as input to the model, where you then ask the model to ask you questions exhaustively until it knows exactly what to do in order to accomplish your goal
2
2
25
2,403
*taps the sign*
x.com/sidbing/status/2054971…
I’m sorry that you’re this desperate that you will take such an unscientific benchmark instead of any established one.
Also qwen local is one of the most random length models there is with all its looping. And we smoke you all on quality benchmarks on every open model. Here’s wildclawbench by internlm, same speed on open models, much better results.
8
1,757
