Hacker News: beering

New comment by beering in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

beering — Mon, 06 Apr 2026 17:55:11 +0000

people have been complaining about this since GPT-4 and have never been able to provide any evidence (even though they have all their old conversations in their chat history). I think it’s simply new model shininess turning into raised expectations after some amount of time.

New comment by beering in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

beering — Sat, 04 Apr 2026 01:25:07 +0000

Word on the street is that Opus is much much larger of a model than GPT-5.4 and that’s why the rate limits on Codex are so much more generous. But I guess you could also just switch to Sonnet or Haiku in Claude Code?

New comment by beering in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

beering — Sat, 04 Apr 2026 01:21:10 +0000

Claude Code is not a platform and you’re not meant to be building on it. Netflix is also not a platform and you shouldn’t be running code (open source or not) to mass download Netflix movies either.

New comment by beering in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

beering — Sat, 04 Apr 2026 01:16:05 +0000

They have so much mindshare right now that they can’t lose, and the number of users that use opencode and would be affected is miniscule—-on the level of complaining about your online bank not supporting Konqueror.

New comment by beering in "Build123d: A Python CAD programming library"

beering — Mon, 30 Mar 2026 16:08:05 +0000

Mainly OpenSCAD is not a BRep modeling tool! It is not on the same level of power as CAD tools with a BRep kernel and this especially shows when you want to do a fillet over an arbitrary edge. Unfortunately these kernels are hard to make and integrate and I only know of two open-source BRep kernels out there: OpenCASCADE (used by FreeCAD and build123) and truck (not sure what the status of it is).

New comment by beering in "ChatGPT Won't Let You Type Until Cloudflare Reads Your React State"

beering — Sun, 29 Mar 2026 20:55:25 +0000

They already see everything I’m doing because I send my prompts to them. What “workaround” are you referring to?

New comment by beering in "ChatGPT won't let you type until Cloudflare reads your React state"

beering — Sun, 29 Mar 2026 20:37:40 +0000

So are you able to get free inference now that you decrypted this?

New comment by beering in "Cross-Model Void Convergence: GPT-5.2 and Claude Opus 4.6 Deterministic Silence"

beering — Sun, 22 Mar 2026 15:33:30 +0000

This is 100% crank “science” that has wrapped up a banal finding in big words and LaTeX. The claim is roughly as exciting as, “some computer programs print nothing to stdout.”

The output shown is not “null” or “void”. It is the empty string, which these LLMs are perfectly capable of outputting. Technically, it outputs the stop token, analogous to \0 at the end of a C string.

New comment by beering in "Tesla has to pay historic $243M judgement over Autopilot crash, judge says"

beering — Fri, 20 Feb 2026 19:23:41 +0000

Doesn’t basic airplane autopilot just maintain flight level, speed, and heading? What are some other things it can do?

New comment by beering in "The Problem with LLMs"

beering — Thu, 12 Feb 2026 05:07:11 +0000

Simultaneously, if you hire human translators, you are likely to get machine translations. Maybe not often or overtly, but the translation industry has not been healthy for a while.

New comment by beering in "How did Windows 95 get permission to put Weezer video 'Buddy Holly' on the CD?"

beering — Wed, 11 Feb 2026 01:28:48 +0000

Is “Start Me Up” the song that goes, “you make a grown man cry”?

New comment by beering in "Our approach to advertising"

beering — Fri, 16 Jan 2026 19:43:26 +0000

I think Google has already shown that in the long run, people accept ads and prefer them to paying a subscription fee. If that weren’t true, then YouTube Premium would have double-digit % of youtube users and Kagi Search would be huge.

New comment by beering in "Gamers Are Overwhelmingly Negative About Gen AI in Video Games"

beering — Fri, 19 Dec 2025 19:01:01 +0000

That may be true, but you can’t compare average GenAI with the best humans because there are many reasons the human output is low quality: budget, timelines, oversights, not having the best artists, etc. Very few games use the best human artists for everything.

Same with programming. The best humans write better code than Codex, but the awful government portals and enterprise apps you’re using today were also written by humans.

New comment by beering in "GPT-5.2"

beering — Thu, 11 Dec 2025 18:46:40 +0000

Model capability improvements are very uneven. Changes between one model and the next tend to benefit certain areas substantially without moving the needle on others. You see this across all frontier labs’ model releases. Also the version numbering is BS (remember GPT-4.5 followed by GPT-4.1?).

New comment by beering in "Anthropic's Prompt Engineering Tutorial (2024)"

beering — Sun, 12 Oct 2025 04:25:42 +0000

Note that this is not relevant for reasoning models, since they will think about the problem in whatever order it wants to before outputting the answer. Since it can “refer” back to its thinking when outputting the final answer, the output order is less relevant to the correctness. The relative robustness is likely why openai is trying to force reasoning onto everyone.

New comment by beering in "Cost of AGI Delusion:Chasing Superintelligence US Falling Behind in Real AI Race"

beering — Sat, 27 Sep 2025 15:23:41 +0000

This article spent a lot of words to say very little. Specifically, it doesn’t really say why working towards AGI doesn’t bring advancements to “practical” applications and why the gazillion AI startups out there won’t either. Instead, we need Trump to step up?

More and more I feel like these policy articles about AI are an endless stream of slop written by people who aren’t familiar with and have never worked on current AI.

New comment by beering in "ChatGPT Pulse"

beering — Fri, 26 Sep 2025 00:13:18 +0000

That’s an interesting point. It’s not hard to imagine that LLMs are much more intelligent in areas where humans hit architectural limitations. Processing tokens seems to be a struggle for humans (look at how few animals do it overall, too), but since so much of the human brain is dedicated to movement planning, it makes sense that we still have an edge there.

New comment by beering in "Dark patterns killed my wife's Windows 11 installation"

beering — Fri, 19 Sep 2025 00:57:36 +0000

The past few years I’ve been hearing crazy stories of workarounds and scripts to deal with all these new features in Windows. Isn’t that what was preventing people from using Linux? Replacing utilman.exe with cmd.exe is not something a normal user would ever do.

New comment by beering in "Taco Bell rethinks AI drive-through after man orders 18,000 waters"

beering — Fri, 29 Aug 2025 16:19:14 +0000

That is what happened in the 18,000 water cups video. It was presented as a way to avoid the ai and get a human on the other end.

New comment by beering in "The Enterprise Experience"

beering — Sun, 17 Aug 2025 22:40:40 +0000

> Does "career development" just mean "more money"?

Big companies means more opportunities to lead bugger project. At a big company, it’s not uncommon to in-house what would’ve been an entire startup’s product. And depending on the environment, you may work on several of those project over the course of a few years. Or if you want to try your hand at leading bigger teams, that’s usually easier to find in a big company.

> Is it still satisfying if that software is bad, or harms many of those people?

There’s nothing inherently good about startups and small companies. The good or bad is case-by-case.