Hacker News: sudhirb

New comment by sudhirb in "CEO Asks ChatGPT to Void $250M Contract, Ignores Lawyers, Loses Terribly"

sudhirb — Tue, 17 Mar 2026 00:30:56 +0000

Is this not the good kind of problem to have? Subnautica 2 is doing so well that the developers get their earn-out bonus?

Seems like pure profit-maximizing/greed!

New comment by sudhirb in "How long does it take to get last liquid drops from kitchen containers?"

sudhirb — Fri, 13 Mar 2026 05:43:22 +0000

I can hardly believe my eyes! I helped do some related research specifically concerning thin-film drainage from tubes, way back in my undergraduate days: https://doi.org/10.1016/j.expthermflusci.2018.04.015

New comment by sudhirb in "Making MCP cheaper via CLI"

sudhirb — Thu, 26 Feb 2026 01:07:59 +0000

a 90% saving is huge isn't it?

for long agent sessions, I would expect a very high cache hit rate unless you're editing the system prompt, tools, or history between turns, or some turns take longer than the cache timeout

New comment by sudhirb in "Something Big Is Happening"

sudhirb — Tue, 10 Feb 2026 23:59:29 +0000

So long as perceived LLM skill is still "spiky" - e.g. within a domain, still showing relatively high variation in ability (often depending on the task or user, to be fair), people will continue to dismiss it

New comment by sudhirb in "Gitmeh: AI-powered Git commits for the terminally lazy"

sudhirb — Tue, 10 Feb 2026 23:51:18 +0000

In the general case I think this is a great idea - if we do a good job of documenting intent etc. in commit messages, agents have an easier time understanding why lines of code exist with no additional specs/mechanisms/etc.

Interested to see what techniques in this area pull ahead and gain traction!

New comment by sudhirb in "AI can 10x developers in creating tech debt"

sudhirb — Sat, 24 Jan 2026 11:21:59 +0000

Coding agents are such a congested space right now that to me this mostly reads as an advertisement.

New comment by sudhirb in "Doing gigabit Ethernet over my British phone wires"

sudhirb — Sat, 24 Jan 2026 11:16:45 +0000

I have 150Mb/s FTTP for £37/month - upgrading to gigabit would be £75/month, for example!

New comment by sudhirb in "ADSL over Wet String"

sudhirb — Fri, 23 Jan 2026 22:47:02 +0000

Interesting that non-salty water didn't make the string conductive(?) enough - I'd have thought that there might have been enough soluble stuff in string.

Also I believe this person runs the ISP I use (and I couldn't speak more highly of it - Andrews & Arnold).

New comment by sudhirb in "Turso is an in-process SQL database, compatible with SQLite"

sudhirb — Fri, 23 Jan 2026 22:40:50 +0000

For me, a lot of the draw is that it's cheaper than managed db services for small/toy projects of mine (that I don't want to use dynamo db for) - that and in a previous job it was useful as relatively temporary multi-tenant storage.

New comment by sudhirb in "Prepare for That Stupid World"

sudhirb — Fri, 19 Dec 2025 18:07:03 +0000

The partner for these projects has a benchmark that the top frontier LLM labs seem to be running on their new model releases - I think there's _some_ value to these numbers in helping people compare and contrast model performance.

https://andonlabs.com/evals/vending-bench

CTO bench: an online LLM coding benchmark

sudhirb — Fri, 19 Dec 2025 18:03:27 +0000

Article URL: https://cto.new/bench

Comments URL: https://news.ycombinator.com/item?id=46328855

Points: 3

# Comments: 0

New comment by sudhirb in "Smartphones manipulate our emotions and trigger our reflexes"

sudhirb — Tue, 28 Oct 2025 15:33:34 +0000

I think that "manipulate people for financial and political gain" is an outcome of what social media companies actually do - I was under the belief that in a general sense, they want to maximise the time people spend on their apps so that they can sell this attention to advertisers, independent of whether or not a given ad buyer wants to manipulate people.

New comment by sudhirb in "Smartphones manipulate our emotions and trigger our reflexes"

sudhirb — Tue, 28 Oct 2025 14:36:44 +0000

Some mild whataboutery: is the purpose of a cancer ward to fail to cure a large fraction of its patients[0]?

https://www.astralcodexten.com/p/come-on-obviously-the-purpo...

New comment by sudhirb in "Teen gamer who 'performed miracles' set to become first millennial saint"

sudhirb — Sun, 07 Sep 2025 09:21:36 +0000

Both miracles are illness-recovery related and feel to me quite like regression to the mean, but I can imagine this is somewhat of a strategic move from the Catholic church to bring some relatability into things.

New comment by sudhirb in "Warp Code: the fastest way from prompt to production"

sudhirb — Wed, 03 Sep 2025 17:03:10 +0000

For me, the USP Warp used to have was generating shell commands from prompts inside the terminal - but Cursor has had this in its embedded terminal for a while now so increasingly I find myself using Ghostty instead

New comment by sudhirb in "How did .agakhan, .ismaili and .imamat get their own TLDs?"

sudhirb — Fri, 29 Aug 2025 19:24:09 +0000

the icann wiki has some articles for these:

https://icannwiki.org/.agakhan

https://icannwiki.org/.ismaili

https://icannwiki.org/.imamat

New comment by sudhirb in "Some thoughts on LLMs and software development"

sudhirb — Thu, 28 Aug 2025 21:33:17 +0000

> One of the consequences of this is that we should always consider asking the LLM the same question more than once, perhaps with some variation in the wording. Then we can compare answers, indeed perhaps ask the LLM to compare answers for us. The difference in the answers can be as useful as the answers themselves.

There was once a coding agent which achieved SOTA performance on SWE Bench Verified by "just" running the agent 5 times on each instance, scoring each attempt and picking the attempt with the highest score: https://aide.dev/blog/sota-bitter-lesson

New comment by sudhirb in "Try and"

sudhirb — Mon, 11 Aug 2025 14:49:24 +0000

Anecdotally I think I have heard "what all" most commonly spoken by Indian English speakers - though that's probably quite far outside the scope of this site.

New comment by sudhirb in "The current state of LLM-driven development"

sudhirb — Sun, 10 Aug 2025 16:53:16 +0000

>Ah yes. An unverifiable claim followed by "just google them yourself".

Some agent scaffolding performs better on benchmarks than others given the same underlying base model - see SWE Bench and Terminal Bench for examples.

Some may find certain background agents better than others simply because of UX. Some background agents have features that others don't - like memory systems, MCP, 3rd party integrations, etc.

I maintain it is easy to search for examples of background coding agents that are not Jules or Copilot. For me, searching "background coding agents" on google or duckduckgo returns some of the other examples that I mentioned.

New comment by sudhirb in "Open Lovable"

sudhirb — Sun, 10 Aug 2025 12:05:51 +0000

It appears that e2b runs Firecracker microVMs (https://e2b.dev/blog/how-manus-uses-e2b-to-provide-agents-wi...)

It shouldn't be too hard to get a Firecracker orchestrator running locally - the articles here were very helpful when I was doing this myself: https://jvns.ca/blog/2021/01/23/firecracker--start-a-vm-in-l...