Hacker News: theLiminator

New comment by theLiminator in "Why skilled workers come to Germany and then leave again"

theLiminator — Tue, 07 Jul 2026 19:45:00 +0000

> Much more than any other country on Earth.

What about Canada?

New comment by theLiminator in "No LLM Code in Dependencies"

theLiminator — Thu, 02 Jul 2026 20:29:46 +0000

If anything I think discipline and rigor will go up.

I think it will force us to adopt stronger type systems, formal methods, and more automated verification.

New comment by theLiminator in "Claude Sonnet 5"

theLiminator — Tue, 30 Jun 2026 18:11:07 +0000

Seems like the way to go for any smaller models is to only use the low reasoning levels, and for anything where you'd want it to reason harder, to just use a larger model.

In effect, high reasoning only makes sense when you're using the frontier model and need extra performance (higher levels of reasoning are never pareto optimal unless you're at the largest model size).

New comment by theLiminator in "I rewrote PostHog's SQL parser, 70x faster, while barely looking at the code"

theLiminator — Wed, 24 Jun 2026 20:34:41 +0000

This is the type of problem for which LLM generation is great for.

If you have an oracle, and your problem is largely just a pure function, it's pretty good at generating something that both works and is fast.

New comment by theLiminator in "Plotnine"

theLiminator — Tue, 23 Jun 2026 18:37:39 +0000

How does this compare with vega/vega-lite?

New comment by theLiminator in "The Harajuku Moment"

theLiminator — Thu, 18 Jun 2026 18:51:55 +0000

I personally skip breakfast and just eat lunch and dinner.

I'm not very active, and I've found that doing that as well as not eating snacks, sugar, or having calories in drinks makes it pretty easy to roughly be calorically neutral day to day.

New comment by theLiminator in "Anthropic apologizes for invisible Claude Fable guardrails"

theLiminator — Thu, 11 Jun 2026 17:42:26 +0000

This take is ridiculous, the PRC is not going to care at all about US regulations.

New comment by theLiminator in "If Claude Fable stops helping you, you'll never know"

theLiminator — Wed, 10 Jun 2026 17:16:36 +0000

I don't disbelieve a 5000x speedup is possible, I disbelieve that a modern day supercomputer will fit in your pocket in even the next 10 years.

New comment by theLiminator in "If Claude Fable stops helping you, you'll never know"

theLiminator — Wed, 10 Jun 2026 05:45:56 +0000

Yes, I'm talking about a supercomputer from today in your pocket. That probably requires at least 5000x perf/watt if not even more.

New comment by theLiminator in "If Claude Fable stops helping you, you'll never know"

theLiminator — Wed, 10 Jun 2026 00:04:25 +0000

> But, history says the supercomputer of today will fit in your pocket in a few years.

I don't think this will be true in the same time span anymore. Each miniaturization is costing more and more money.

Perhaps they'll come up with exotic fundamental improvements, but I don't think the rate of improvement of compute/watt will match the previous decades.

New comment by theLiminator in "Claude Fable 5"

theLiminator — Tue, 09 Jun 2026 21:50:52 +0000

> it's a cat and mouse game that favors the defenders IMO

How so? I'm actually against most of the "safety-tuning" that anthropic does, but this seems fundamentally untrue, a close analogue being video game cheat development. I think in general the cheat developer has an advantage and the cheats generally proliferate for quite a while before being patched.

New comment by theLiminator in "Claude Fable 5"

theLiminator — Tue, 09 Jun 2026 18:19:09 +0000

This is pretty bullshit, now you have no idea if your output is getting silently nerfed.

New comment by theLiminator in "Claude Fable 5"

theLiminator — Tue, 09 Jun 2026 18:07:21 +0000

> We have also added safeguards related to frontier LLM development. As discussed in Section 6.1 of our February 2026 Risk Report, we are concerned about the risks of accelerating the overall pace of AI development, though we remain uncertain about the severity of these risks. In particular, our concern is with—as we wrote then—“accelerating other AI developers in building powerful AI systems that pose similar risks to the ones ours pose - without necessarily having commensurate safeguards.” In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restriction through our safeguards avoids accelerating the actors most willing to violate these terms. Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts, these safeguards will not be visible to the user. Fable 5 will not fall back to a different model. Instead, the safeguards will limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT). These interventions will not affect the vast majority of coding work. We estimate they will impact ~0.03% of traffic, concentrated in fewer than 0.1% of organizations. When these interventions are active, we expect them to have minimal behavioral impact on the model except to limit its effectiveness in developing frontier LLMs. Claude will still respond helpfully to user requests. We’ll continue to improve the precision of our detection methods following the launch of this model.

This seems pretty bullshit, you're paying through the nose for tokens and if you are doing anything ML-adjacent, you might silently get worse output without knowing it.

New comment by theLiminator in "The Public Should Own Half of the Big A.I. Companies"

theLiminator — Wed, 03 Jun 2026 17:59:23 +0000

This would have a massive chilling effect on the private sector as a whole. IMO it would completely destroy investment in America. American companies and markets get extraordinary investor interest due to strong property rights. Once those rights are gone there will be massive capital flight and greatly reduced investment.

Imo this proposal is even worse than a billionaire wealth tax (which has all sorts of implementation issues).

New comment by theLiminator in "The Pirate Bay Remains Resilient, 20 Years After the Raid"

theLiminator — Mon, 01 Jun 2026 21:53:59 +0000

I'm curious why IPFS never took off (I haven't dug into it much), but it seems more decentralized than BT.

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

theLiminator — Sat, 30 May 2026 21:49:01 +0000

Then what do you mean by pure software? I think there's essentially zero domain-free software.

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

theLiminator — Sat, 30 May 2026 21:37:54 +0000

> Writing software has never been difficult.

That's not true at all, sure CRUD might not have been that difficult, but absolutely there is extremely complicated software out there that is really difficult to write in a performant and correct manner.

New comment by theLiminator in "Dynamic Workflows in Claude Code"

theLiminator — Thu, 28 May 2026 19:16:50 +0000

Is there not a reason to instead port claude code to rust? Do you have internal benchmarks that show that claude code is better at typescript than rust?

New comment by theLiminator in "The operating cost of adult and gambling startups"

theLiminator — Fri, 24 Apr 2026 18:28:01 +0000

How about social media companies, or quasi-monopoly employees (essentially all of FANGMAN)?

What about pharma and for-profit healthcare employees?

New comment by theLiminator in "GPT-5.5"

theLiminator — Thu, 23 Apr 2026 19:56:13 +0000

> Productivity metrics were better when businesses were run on just pen and paper

What metrics are these?