atharva
@atharvaraykar.com
📤 109
📥 197
📝 78
i write at atharvaraykar.com i work
@nilenso.com
yes-anding the world.
My colleague analysed the system prompts for codex and claude and realised the reason they feel different is because of deliberate product decisions in the prompt!
blog.nilenso.com/blog/2026/02...
loading . . .
Codex CLI vs Claude Code on autonomy
https://blog.nilenso.com/blog/2026/02/12/codex-cli-vs-claude-code-on-autonomy/
about 1 month ago
0
6
0
I was hoping the OpenResponses API would be a meaningful step forward deal with the LLM API standardisation headaches, but right now the spec is really undercooked. There are lots of inconsistencies/contradictions between the reference schemas and what the specification says!
www.openresponses.org
loading . . .
Open Responses
Open Responses documentation overview.
https://www.openresponses.org/
about 1 month ago
1
2
0
Is A2A protocol completely useless? I don't know of anyone building enterprise multi-agent communication. Why design such a thick protocol for a use case that does not yet exist in practice?
a2a-protocol.org/latest/
Feels like another SOAP/CORBA etc
loading . . .
A2A Protocol
The official documentation for the Agent2Agent (A2A) protocol. The A2A protocol is an open standard that allows different AI agents to securely communicate, collaborate, and solve complex problems tog...
https://a2a-protocol.org/latest/
about 1 month ago
1
1
0
thoughts on ese.
atharvaraykar.com/ese/
loading . . .
Ese
Large language models are better thinkers than writers. Well okay, they don't think as humans do, but I've been letting it write the vast chunk of my computer programs over the last year or so, which ...
https://atharvaraykar.com/ese/
about 1 month ago
1
3
1
things I have dumped on the internet this month. How the lobsters algorithm works:
atharvaraykar.com/lobsters/
11:59 PM:
atharvaraykar.com/reinforce/
loading . . .
How the Lobsters front page works
Lobsters is a computing-focused community centered around link aggregation and discussion. The code is open source, so I had a look at how the front page algorithm works. This is it: $$\textbf{hotn...
https://atharvaraykar.com/lobsters/
about 2 months ago
0
1
0
I wrote a post looking into multiple SWE/coding benchmarks. Many of them measure something narrower than what their names suggests.
blog.nilenso.com/blog/2025/09...
6 months ago
0
1
1
Wrote about units of work being a useful lever for getting good results from AI-assisted coding.
blog.nilenso.com/blog/2025/09...
6 months ago
0
1
1
I've been poking Srihari, our most experienced engineer
@nilenso.com
to share his hard-earned knowledge for the benefit of others. Even if you're not an engineering leader like me, this checklist gives a lot of insight into what makes a great engineering org.
blog.nilenso.com/blog/2025/09...
6 months ago
0
2
2
grateful for my low-quality education where teachers could not correctly explain the basics of anything right it pushed me to cultivate good epistemics and build truth-seeking habits early on it also forced me to never trust authoritative figures, many are very incompetent
7 months ago
0
0
0
Why Does AI Feel So Different? An enjoyable read from my colleague, Srihari. We've been talking about why this disruption feels different from other recent technological disruptions and he captured a lot of that really well in this post. Link:
blog.nilenso.com/blog/2025/08...
7 months ago
1
0
1
Question for the "launch many parallel claude agents to go faster" crowd: Why isn't that the same problem as the Brooks's law all over again?
8 months ago
0
0
0
despite all the AI hype there's only been two kinds of tools with direct improvements to my life: - chat (like chatgpt, claude ai) - terminal coding agents (like claude code) surprising how nothing better has stuck yet
8 months ago
1
1
0
Several people ask me about how I'm keeping up with all the AI things and finding signal in this noisy landscape. I wrote a guide explaining this.
blog.nilenso.com/blog/2025/06...
9 months ago
0
4
1
I was seeing
@karpathy.bsky.social
's Software 3.0 talk, as one should. Surreal to see him recommend my writing to make a point on AI-assisted coding "Is that me on TV??" moment
9 months ago
4
9
1
reposted by
atharva
Simon Willison
9 months ago
I loved it!
simonwillison.net/2025/Jun/10/...
loading . . .
AI-assisted coding for teams that can’t get away with vibes
This excellent piece by Atharva Raykar offers a bunch of astute observations on AI-assisted development that I haven't seen written down elsewhere. Building with AI is fast. The gains in …
https://simonwillison.net/2025/Jun/10/ai-assisted-coding/
0
7
3
Quality, and the cutlets of enthusiasm
atharvaraykar.com/quality-and-...
loading . . .
Quality, and the cutlets of enthusiasm
Zen and the art of motorcycle maintenance was on my reading wishlist for a while. From the title, I assumed the book would be something like a tasteful self-help book, a quirky blend of kōanic mystici...
https://atharvaraykar.com/quality-and-the-cutlets-of-enthusiasm/
10 months ago
1
3
2
I have revamped my website of essays. it's now more searchable, supports commenting and also doubles as a newsletter. now back to writing again.
loading . . .
atharva's internet place
tldraw is canvas software that runs on your browser (like MS Paint, excalidraw etc). This project caught my attention when I saw demos of fun AI experiments with the canvas interface*. Even the plain…
https://buff.ly/3EbtE28
about 1 year ago
1
0
0
is "cracked" the new codeninja/rockstar?
about 1 year ago
0
0
0
Buddhist Teacher Geshe Langri Tangpa (circa 1100 AD) 🤝 XXXTentacion (2018)
about 1 year ago
0
1
0
reposted by
atharva
Simon Willison
about 1 year ago
General consensus in the replies and quotes of this seems to be that the entire concept of "AI skills" is a joke - how hard is typing text into a chatbot, really? I will continue to argue that it's genuinely difficult, and that the challenge in using these tools is widely underestimated
add a skeleton here at some point
34
321
64
the reason i write and encourage other people to write is because writing is the most scalable form of persuasion and negotiation it's one of the best coordination mechanisms that humans have
about 1 year ago
0
0
0
my current pet conspiracy theory is that a lot of your favourite artists are heavily using AI generated sequences in their music, but no one has noticed it yet
about 1 year ago
1
1
0
TIL about the Modi (मोडी / 𑘦𑘻𑘚𑘲) script, used for Marathi up until the 1940s. In 2025, it looks like AI generated Devanagari.
about 1 year ago
0
4
1
reposted by
atharva
Daniel Burka
about 1 year ago
One of our engineers wrote a thoughtful article about how public health challenges can be framed using "Systems Thinking"
@atharvaraykar.com
www.simple.org/blog/a-syste...
loading . . .
A ‘systems thinking’ approach to saving lives from heart attacks and strokes
A technologists’ skill set of crafting scalable solutions works well on notoriously hard problems like public health. The way to make it approachable is to adopt ‘systems thinking’.
https://www.simple.org/blog/a-systems-thinking-approach-to-saving-lives-from-heart-attacks-and-strokes/
1
14
2
The most meaningful work I've ever done has been with the wonderful tech team who work on the
simple.org
app. I wrote on the Simple blog about how ideas from systems dynamics can be used to make sense of hard problems like preventing deaths from heart disease.
www.simple.org/blog/a-syste...
loading . . .
A ‘systems thinking’ approach to saving lives from heart attacks and strokes
A technologists’ skill set of crafting scalable solutions works well on notoriously hard problems like public health. The way to make it approachable is to adopt ‘systems thinking’.
https://www.simple.org/blog/a-systems-thinking-approach-to-saving-lives-from-heart-attacks-and-strokes/
about 1 year ago
1
1
1
i quickly concocted a writer's block unblocker (with
@tldraw.com
computer) it takes an oblique strategy (from the brian eno et al card deck) and uses it to provide unhinged critique of the essay you are working on to help you break out of a rut link to program:
computer.tldraw.com/t/4KoB33nFEr...
loading . . .
about 1 year ago
1
9
2
i picked up india after gandhi by ramachandra guha recently and it is a 10/10 book so far it has renewed my fascination with india context is that which is scarce. this book will catch you all up with some context
about 1 year ago
0
1
1
i figured out how to use twttr without frying my brain
https://buff.ly/3DIRL7W
about 1 year ago
1
0
0
wrote a short note on why i approach everything with optimism tldr; - optimism is the ultimate form of ownership - cynicism is the rejection of ownership - hard to be curious when you're always cynical
loading . . .
I discovered that I'm radically optimistic.
I'm still struggling to convey what that means. Or if that's even the right phrase for it. it may just be these every cloud has a silver...
https://buff.ly/3VWqc1t
about 1 year ago
1
2
1
'tapestry' is another linguistic casualty of LLMs
about 1 year ago
0
0
0
"god is in the details" unexpectedly resonant phrase from conan o'brien and a common thread tying most things i look up to
over 1 year ago
0
0
0
thindi places get a bad rep sometimes for being "dirty". many aren't, they just don't match your aesthetics of cleanliness i'd still rate those kitchens as multiple levels cleaner than the avg bangalore tech person bachelor pad kitchen
over 1 year ago
1
5
1
I *occasionally* see complaints here about far-right trolls and toxicity on the twttr, and I complaints on the twttr about far-left virtue signal moralistic trolls on here. I experience neither on either—I'm either weirdly good at curating my feed or not famous enough?
over 1 year ago
2
0
0
menu highlights
over 1 year ago
0
2
0
art in a white wall big box chamber is gazed upon for long, an object of loving attention art outside the door of hae kum gang korean restaurant gents toilet is ignored among the din of swinging doors and flushing toilets
over 1 year ago
0
2
0
chai darkening ideas - add fine mud - spray spray tan - mix in water from a lake in peenya - chocolate - blend with chyawanprash
loading . . .
over 1 year ago
0
1
0
bluesky has no gifs bluesky has no support for 1834 x 1048 video ew
over 1 year ago
0
0
0
in case you missed it, the current thing I'm doing with my life is making esoteric thindi hopping videos
youtu.be/nZfKcNHs0SI?...
#bangalore
??
#dosa
??
#idly
????
loading . . .
slv indranna hotel: soft idly and dosE
YouTube video by Atharva Raykar
https://youtu.be/nZfKcNHs0SI?si=t00wJSmO274Ub-CR
over 1 year ago
1
2
1
you reached the end!!
feeds!
log in