Hacker News: ldjkfkdsjnv

New comment by ldjkfkdsjnv in "Ask HN: Is anyone using Super Grok Heavy for code?"

ldjkfkdsjnv — Wed, 16 Jul 2025 18:57:01 +0000

o3 pro is really good, but the context is really constrained, so its hard to use and doesnt output enough. This makes it suitable for ideating on good abstractions, but cant really make broad sweeping changes. Grok will output a full file. If you use the o3 pro API, its actually great, but it gets really expensive.

New comment by ldjkfkdsjnv in "Ask HN: Is anyone using Super Grok Heavy for code?"

ldjkfkdsjnv — Wed, 16 Jul 2025 03:49:51 +0000

I think its much better than opus. I would describe its code output as boring and to the point, no fluff. O3 Pro is better at abstraction, but grok heavy is better at bug hunting, and only doing exactly as needed. I swapped my openai pro license for grok, its good. Another big advantage is the context window size. Honestly I use these models all day long, and have felt that while sonnet 3.5 was ground breaking, but that anthropic is behind google, openai, and now xai.

For tools, I use repo prompt + grok website. Personally think claude code is overrated, and hand building the context by selecting the files is far better for complicated tasks

New comment by ldjkfkdsjnv in "Co-founder exiting after pivot – what's a fair exit package?"

ldjkfkdsjnv — Fri, 11 Jul 2025 03:05:37 +0000

It happens all the time, I have seen it in NYC. Usually its an early stage thing, cofounder leaves after 1 year etc. Much harder to do with a complicated cap table. Investors I could name even suggest it

New comment by ldjkfkdsjnv in "Jane Street barred from Indian markets as regulator freezes $566M"

ldjkfkdsjnv — Sun, 06 Jul 2025 22:51:28 +0000

all that OCAML we only hire the smartest is often a veil for what is really a simpler operation that is borderline illegal. probably alot of employees dont even really understand the systems they work on

New comment by ldjkfkdsjnv in "Jane Street barred from Indian markets as regulator freezes $566M"

ldjkfkdsjnv — Sun, 06 Jul 2025 22:49:25 +0000

I know someone that made 10 million a year for a long time on wall street. They said, generally you can assume anyone making a large amount of money is a criminal. Any large deviations from the typical returns you would see in an asset class was suspicious

New comment by ldjkfkdsjnv in "Nvidia won, we all lost"

ldjkfkdsjnv — Sat, 05 Jul 2025 22:05:22 +0000

theres alot of shadow banning, up ranking and down ranking

New comment by ldjkfkdsjnv in "We're all CTO now"

ldjkfkdsjnv — Sat, 05 Jul 2025 13:10:43 +0000

This post is completely false

New comment by ldjkfkdsjnv in "Ask HN: How to make money with SaaS without network or VC funding?"

ldjkfkdsjnv — Sat, 05 Jul 2025 04:39:47 +0000

dont write any software until you have a product you are getting easy sales with, forget you even know how to code

New comment by ldjkfkdsjnv in "OBBB signed: Reinstates immediate expensing for U.S.-based R&D"

ldjkfkdsjnv — Sat, 05 Jul 2025 04:29:11 +0000

ive been coding 5+ hours a day almost every day for 15 years. i think ai will replace 70% of SWE in the near future. not employement, but 70% of the current work done by engineers

New comment by ldjkfkdsjnv in "Ask HN: How did Soham Parekh get so many jobs?"

ldjkfkdsjnv — Fri, 04 Jul 2025 16:44:25 +0000

all the jobs are being outsourced is why

New comment by ldjkfkdsjnv in "Ask HN: How did Soham Parekh get so many jobs?"

ldjkfkdsjnv — Fri, 04 Jul 2025 16:32:04 +0000

people above and around you prefer if you stay within the range. over performing stresses other people out and causes conflict.

New comment by ldjkfkdsjnv in "Ask HN: Is there a business for extracting US tech talent?"

ldjkfkdsjnv — Fri, 04 Jul 2025 02:17:06 +0000

Yeah its called wipro/infosys/cognizant

New comment by ldjkfkdsjnv in "What to build instead of AI agents"

ldjkfkdsjnv — Thu, 03 Jul 2025 01:16:27 +0000

if you are in a competitive market you will lose with this approach

New comment by ldjkfkdsjnv in "What to build instead of AI agents"

ldjkfkdsjnv — Thu, 03 Jul 2025 00:49:31 +0000

This is all going to be solved by better models. Building agents is building for a world that doesn't quite exist yet, but probably will in a year or two. Building some big heuristic engine that strings together LLM calls (which is what this blog advocates for) is essentially a bet against progress in ai. I'm not taking that bet, and neither are any of the major players.

New comment by ldjkfkdsjnv in "How many PhDs does world need? Doctoral graduates outnumber academia jobs"

ldjkfkdsjnv — Tue, 24 Jun 2025 01:07:27 +0000

phd programs are largely immigration backdoors

New comment by ldjkfkdsjnv in "Ask HN: At what point did your startup hire its first lawyer?"

ldjkfkdsjnv — Mon, 23 Jun 2025 02:53:02 +0000

The second you have a cofounder/business partner you need a lawyer

New comment by ldjkfkdsjnv in "We’ve had a Denisovan skull since the 1930s, only nobody knew"

ldjkfkdsjnv — Mon, 23 Jun 2025 01:35:36 +0000

Dark truths are hidden in ancient dna

New comment by ldjkfkdsjnv in "AI is ushering in a “tiny team” era"

ldjkfkdsjnv — Sat, 21 Jun 2025 19:33:11 +0000

Theres two types of software, the ones no one uses, and the ones people complain about

New comment by ldjkfkdsjnv in "AI is ushering in a “tiny team” era"

ldjkfkdsjnv — Sat, 21 Jun 2025 19:32:15 +0000

I think this is the beginning of the end of early stage venture capital in b2b saas. Growth capital will still be there, but increasingly there will be no reason to raise. It will empower individuals with actual skill sets, rather than those with fancy schools on their resume

New comment by ldjkfkdsjnv in "Is there a half-life for the success rates of AI agents?"

ldjkfkdsjnv — Wed, 18 Jun 2025 13:32:32 +0000

another article on xyz problem with LLMs, which will probably be solved by model advancements in 6/12 months.