- Agent Orchestrator, Builder
Joined October 2022
- Tweets 859
- Following 1,183
- Followers 121
- Likes 2,263
143 Photos and videos
Jun 9
20 years from now, the only computer every consumer will have is a phone / a portable device
laptops might be obsolete
1
1
12
Jun 9
We went from super computers to cathode ray tubes with large desktops to flat screens and smaller Mac minis and laptops and phones doing somethings (phones also went through a similar arc) Next agents will fully run on the cloud and do stuff for us
10
Jun 2
Short self-serve crash course on Hermes Agent to build your understanding. Linking in comments:
1
1
2
41
Jun 2
1
1
20
Bhaulik Patel retweeted
Jun 1
how to build anything rn:
- get a hetzner, do, or hostinger vps
- host hermes on it
- add gbrain or implement your own memory vault using qmd sql
- set up hermes with codex auth -> gpt-5.5 / no reasoning / fast mode
- install orca on your macbook and phone with tailscale to have a nice ide to work on both
- before starting any work, ask hermes to conduct deep research on the subject and save it to gbrain as source material for the project
- use the `/grill-me` skill or a similar prompt to uncover as many unknowns as possible. save results to memory too
- define/write clear evals for every project to determine whether a run was successful
- have hermes iterate over the project until all evals pass, saving all learnings to the vault along the way
- whenever it gets stuck, use memory a new research or `/grill-me` session to unblock it
rinse and repeat until the work is done. pay attention to the process. develop a feeling for how long tasks should take and do not be afraid to stop a model mid session to ask for status and why it's taking so long.
72
182
3,249
177,234
Bhaulik Patel retweeted
May 28
84
368
2,559
784,678
.@natfriedman on temperature probing teams through production iteration loops at @GitHub
5
2
21
5,287
Bhaulik Patel retweeted
May 13
115
772
6,251
5,375,312
Bhaulik Patel retweeted
May 9
15
65
440
133,516
Bhaulik Patel retweeted
May 9
i spoke to a founder yesterday - their CTO finally read their agent-made codebase after months and panicked when he realized it was impossible to understand wtf was going on
my rule of thumb is: if your codebase starts written by agents, don’t try to understand it
instead, align at the architectural level before any building happens, and ask the agent to maintain a living architecture diagram of how the system works
there are three altitudes that matter:
- Top-level: architecture
- Mid-level: patterns & abstractions
- Low-level: file-level code
in today’s world, a CTO should be deeply concerned with #1. #2 matters too, but not as critical as #1.
if #1 and #2 are dialed in, #3 is where most of the high leverage agentic gains live.
as long as you understand the architecture and critical interfaces, it becomes much easier to reason about ground truth and meaningfully iterate
understanding and informing the architecture / patterns / abstractions give your codebase maximum longevity and agent maintainability
32
51
485
102,519
May 8
Markdown built the agent era.
But it's quietly become the bottleneck.
1
1
47
May 8
The real reason this works isn't technical.
The author admitted he'd quietly stopped reading Claude's long plans. He trusted the model. Drifted out of the loop.
HTML pulled him back in. Tabs to click. Diagrams to scan. Sliders to nudge.
You stay involved. That's the whole thing.
1
39
May 8
Markdown was the format of the early agent era.
HTML is the format of the era we're in now.
Original piece by Thariq on the Claude Code team - worth reading in full (and yes, it's rendered as HTML):
supacanvas.com/c/pz78hz2q
46