Hacker News: practice9

New comment by practice9 in "Claude for Excel"

practice9 — Mon, 27 Oct 2025 21:02:08 +0000

LLMs are getting quite good at reviewing the results and implementations, though

New comment by practice9 in "Building the mouse Logitech won't make"

practice9 — Mon, 25 Aug 2025 23:34:23 +0000

I find it hilarious/sad that the 0.5x cheaper Ergo M575 has much better design in that regard (just plastic that doesn’t degrade)

New comment by practice9 in "I gave the AI arms and legs then it rejected me"

practice9 — Wed, 06 Aug 2025 08:40:36 +0000

They should have used Claude Code for reviews

New comment by practice9 in "AI coding agents are removing programming language barriers"

practice9 — Wed, 23 Jul 2025 07:06:37 +0000

Humans cannot reason about code at scale. Unless you add scaffolding like diagrams and maps and …

Things that most teams don’t do or half-ass

New comment by practice9 in "Supreme Court's ruling practically wipes out free speech for sex writing online"

practice9 — Sat, 12 Jul 2025 23:30:56 +0000

A variation of “no taxation without representation”?

New comment by practice9 in "Why Claude's Comment Paper Is a Poor Rebuttal"

practice9 — Mon, 16 Jun 2025 10:16:10 +0000

The human is a bad co-author here really.

I deployed lots of high performance, clean, well documented etc code generated by Claude or o3. I reviewed it wrt requirements, added tests and so on. Even with that in mind it allowed me to work 3x faster.

But it required conscious effort on my part to point out issues and inefficiencies on LLMs part.

It is a collaborative type of work where LLMs shine (even in so called agentic flows)

New comment by practice9 in "Sycophancy in GPT-4o"

practice9 — Wed, 30 Apr 2025 08:19:25 +0000

Well the system prompt is still the same for both models, right?

Kinda points to people at OpenAI using o1/o3/o4 almost exclusively.

That's why nobody noticed how cringe 4o has become

New comment by practice9 in "Whistleblower details how DOGE may have taken sensitive NLRB data"

practice9 — Tue, 15 Apr 2025 13:17:27 +0000

Kinda similar in a way to China or Russia “disappearances”

New comment by practice9 in "Gemma 3 Technical Report [pdf]"

practice9 — Wed, 12 Mar 2025 08:44:24 +0000

But who is the target group?

Last time only some groups of enthusiasts were willing to work through bugs to even run the buggy release of Gemma

Surely nobody runs this in production

New comment by practice9 in "Why LLMs still suck at OCR"

practice9 — Fri, 07 Feb 2025 21:38:37 +0000

I tried the square example from the paper mentioned with o1-pro and it had no problem counting 4 nested squares…

And the 5 square variation as well.

So perhaps it is just a question of how much compute you are willing to throw at it

New comment by practice9 in "Order Declassifying JFK and MLK Assassination Records [pdf]"

practice9 — Tue, 04 Feb 2025 09:14:02 +0000

With LLMs that even might be automated

New comment by practice9 in "GPT-4o with scheduled tasks (jawbone) is available in beta"

practice9 — Wed, 15 Jan 2025 02:15:23 +0000

Well none of the labs have good frontend or mobile engineers or even infra engineers

Anthropic is ahead in this because they keep their UIs simplistic so the failure modes are also simple (bad connection)

OpenAI is just pushing half baked stuff to prod and moving on (GPTs, Canvas).

Find it hilarious and sad that o1-pro just times out thinking on very long or image-intense chats. Need to reload page multiple times after it fails to reply and maybe answer will appear (or not? Or in 5 minutes?). Kinda shows they’re not testing enough and “not eating their own food” and feels like chatgpt 3.5 ui before the redesign

New comment by practice9 in "Learning not to trust the All-In podcast"

practice9 — Wed, 06 Nov 2024 18:45:51 +0000

One of those guys needs to be fined for the pump & dump scheme (with SPCE: Virgin Galactic), and the other one should be investigated if he was receiving money from the Russian government or influence agents.

New comment by practice9 in "UK will give sovereignty of Chagos Islands to Mauritius"

practice9 — Fri, 04 Oct 2024 10:04:39 +0000

More like reparations

New comment by practice9 in "Floating megabomb heaves to near the English coast"

practice9 — Sun, 29 Sep 2024 10:01:13 +0000

The interesting thing is that ship was damaged almost immediately after leaving the port, had a chance to stop in Russian ports along the way but instead is doing a tour near EU countries.

The crew is either amazingly incompetent or malicious/complicit.

You don’t put a ship that can blow up near: a. Gas&oil terminals, b. military air base

New comment by practice9 in "GPT-4o"

practice9 — Mon, 13 May 2024 19:30:51 +0000

It is cringe overenthusiastic, but a proper instructions/system prompt will fix that mostly

New comment by practice9 in "GPT-4o"

practice9 — Mon, 13 May 2024 19:29:04 +0000

I always double-check even the most obscure facts returned by GPT-4 and have yet to see a hallucination (as opposed to Claude Opus that sometimes made up historical facts). I doubt stuff interesting to kids would be so out of the data distribution to return a fake answer.

Compared to YouTube and Google SEO trash, or Google Home / Alexa (which do search + wiki retrieval), at the moment GPT-4 and Claude are unironically safer for kids: no algorithmic manipulation, no ads, no affiliated trash blogs, and so on. Bonus is that it can explain on the level of complexity the child will understand for their age

New comment by practice9 in "OpenAI Bought Chatgpt.com"

practice9 — Sat, 04 May 2024 18:35:01 +0000

Wasn't it pointing to https://x.ai just a few months ago? Interesting

New comment by practice9 in "World_sim: LLM prompted to act as a sentient CLI universe simulator"

practice9 — Sat, 06 Apr 2024 12:29:04 +0000

teknium / Nous released Mistral finetunes (Hermes) that are quite great, and even published the datasets used for training.

But for the worldsim I think they are really using Claude (probably Haiku or Sonnet) via openrouter (https://openrouter.ai/).

New comment by practice9 in "Meta outage"

practice9 — Tue, 05 Mar 2024 20:34:54 +0000

Interesting. I had a problem a few months ago with DNS not resolving Meta servers on my Starlink internet connection, but I was able to use the UI and the apps nonetheless, just couldn't open the store or update firmware.

Seems like they really did change something in the latest firmwares.