Hacker News: SatvikBeri

New comment by SatvikBeri in "Why Common Lisp is now the best programming language"

SatvikBeri — Tue, 06 Oct 2026 04:49:52 +0000

That really hasn't been my experience, LLMs have done well with Julia since Claude 3.7

New comment by SatvikBeri in "Claude Opus 5.5"

SatvikBeri — Wed, 23 Sep 2026 00:56:12 +0000

I'd be really curious to see benchmarks of haiku vs lower effort on bigger models. My own evals found Fable 5.1 at low to be better than Opus 5 on high.

New comment by SatvikBeri in "You can defeat the Dream Devourer from Chrono Trigger using an int overflow"

SatvikBeri — Sun, 20 Sep 2026 01:55:59 +0000

Similarly, you can defeat the Egg Dragon superboss in Lufia 2 by healing before attacking: it starts with 65,535 HP.

New comment by SatvikBeri in "iPhone Duo"

SatvikBeri — Wed, 09 Sep 2026 19:21:20 +0000

I started paying for phones with really good cameras once I had kids and I wanted to take lots of pictures with them. I definitely notice the quality difference in random, off-the-cuff photos (which is the vast majority), though if I have time to set up a bit, cheaper phones produce pictures that look the same to me.

New comment by SatvikBeri in "Your intellectual fly is open when you use an LLM to author a post (2025)"

SatvikBeri — Sun, 06 Sep 2026 21:46:26 +0000

One example that comes to mind is math textbooks – the early textbooks in a field are usually much worse than later ones that come along. To pick on one, I think most people who've read both would agree that the commutative algebra section of Lang's Algebra is much worse than Atiyah & McDonald's Commutative Algebra book, despite covering basically the same ideas, theorems, etc.

New comment by SatvikBeri in "Anthropic's best AI model struggles to attract users as cheaper tools thrive"

SatvikBeri — Mon, 24 Aug 2026 00:06:04 +0000

I hit it once when I asked a question about whether butterflies remember anything from their time as caterpillars. I've never hit it for coding, but I also don't really do much related to security.

New comment by SatvikBeri in "Claude Opus 5"

SatvikBeri — Sat, 25 Jul 2026 00:16:50 +0000

> We can also imagine the application of these models for malicious purposes , including the following (or other applications we can’t yet anticipate):

  *   Generate misleading news articles

  *   Impersonate others online

  *   Automate the production of abusive or faked content to post on social media

  *   Automate the production of spam/phishing content

Seems like the prediction was pretty accurate.

New comment by SatvikBeri in "GPT-5.6"

SatvikBeri — Thu, 09 Jul 2026 20:22:27 +0000

It's trivial to try another agent. You can spend $20 for a monthly subscription and ask it to import all your settings from Claude Code.

New comment by SatvikBeri in "Are you expected to run five Python type-checkers now?"

SatvikBeri — Tue, 09 Jun 2026 21:51:55 +0000

I use Julia! I like it a lot, and add type parameters to all application code. But JET.jl does not feel anywhere close to the assurances I can get from a statically typed language (yet)

New comment by SatvikBeri in "Are you expected to run five Python type-checkers now?"

SatvikBeri — Mon, 08 Jun 2026 14:56:36 +0000

What statically typed language would you suggest for machine learning and large data pipelines? I don't love Python, but it has by far the largest ecosystem.

New comment by SatvikBeri in "Technical Interviews Reject the Wrong Engineers"

SatvikBeri — Fri, 05 Jun 2026 16:35:14 +0000

Every interview method has some glaring flaws, and I find you mostly have a choice of which flaws you pick.

On my current team, I care a lot about the ability to write fast code. The most important part of my process is a take-home designed to take 2 hours where the main goal is to solve a relatively easy problem as performantly as possible. Answers have varied from 0.2ms – 50ms.

Take-homes have some obvious disadvantages, but overall I find they're better at finding the people we're looking for than just about every other method. But I'm at a small company, hiring for a fairly specialized team. If the situation was different (e.g. I needed to hire 50 people/year) I'd use a much more standard process.

New comment by SatvikBeri in "Domain expertise has always been the real moat"

SatvikBeri — Sun, 31 May 2026 02:51:27 +0000

I'm a fairly moderate user, never hit any kind of usage limits, but I used 44 million cache create tokens and 1.5 billion cache read tokens, which ccusage estimates would have cost $990, and calculates the different categories separately.

New comment by SatvikBeri in "Anthropic raises $65B in Series H funding at $965B post-money valuation"

SatvikBeri — Fri, 29 May 2026 06:13:52 +0000

Not OP, but Dario said on Dwarkesh's podcast 3 months ago that their gross margins are "significantly higher than 50%"

New comment by SatvikBeri in "Anthropic raises $65B in Series H funding at $965B post-money valuation"

SatvikBeri — Thu, 28 May 2026 22:39:11 +0000

Run rate is annualized revenue based on some recent period, e.g. taking the last month of revenue and multiplying by 12. Revenue (classic) is a historical measure, e.g. revenue in 2025.

New comment by SatvikBeri in "What color is your function? (2015)"

SatvikBeri — Tue, 26 May 2026 19:43:45 +0000

Julia does this – you generally write synchronous, single-threaded functions most of the time, and can use code like `t = @spawn foo(b)` to get a Task, and then `output = fetch(t)` to wait for it and get the value.

I like this general approach a lot, it's overall quite nice for Julia's core use case of number crunching, it means you typically make decisions around concurrency at the call sites. Though it does rely heavily on Julia's runtime, and it can be a bit difficult to figure out what's going on under the hood.

New comment by SatvikBeri in "Open source Kanban desktop app that runs parallel agents on every card"

SatvikBeri — Fri, 22 May 2026 22:08:19 +0000

I usually aim to have Claude end up with about 500 lines of code after a night of work. Most of what it's doing is experimenting with many different approaches, summarizing them, and then giving me a relatively small diff to review and modify.

New comment by SatvikBeri in "Zerostack – A Unix-inspired coding agent written in pure Rust"

SatvikBeri — Sat, 16 May 2026 23:28:05 +0000

The context window has nothing to do with RAM usage and even if it did, a million tokens of context is maybe 5mb.

New comment by SatvikBeri in "Elevated error rates on Opus 4.7"

SatvikBeri — Fri, 15 May 2026 05:13:15 +0000

9-5 Pacific Time

New comment by SatvikBeri in "Elevated error rates on Opus 4.7"

SatvikBeri — Fri, 15 May 2026 05:12:43 +0000

Yes, I've pretty much used Opus exclusively for the last year, except for a brief period when Sonnet was ahead

New comment by SatvikBeri in "Elevated error rates on Opus 4.7"

SatvikBeri — Fri, 15 May 2026 01:21:49 +0000

I've never actually run into the issues that people talk about online, like Claude suddenly getting dumb or running out of usage. So there's just not a lot of incentive for me to shop around. I've used Amp a bit, and it's quite nice, but a bit more expensive without the subsidized subscription.