Hacker News: algoth1

New comment by algoth1 in "Opus 4.7 knows the real Kelsey"

algoth1 — Fri, 01 May 2026 17:21:27 +0000

That issue is different, when web tools were added to gpt4o it would fetch the site, and basically copy paste the text into the answer body. So, you were able to read the content of the site without the site getting the ad impressions. Now the system prompts put a very tight word limit - 25? - on quotes from sites the model visits

New comment by algoth1 in "He asked AI to count carbs 27000 times. It couldn't give the same answer twice"

algoth1 — Wed, 29 Apr 2026 13:07:13 +0000

I’ll save you a click: ‘Llms can’t perform direct calorimetry through a photo of a meal. Llms can’t even perform basic atomic spectroscopy’ in other news…

New comment by algoth1 in "Tim Cook Is Leaving. Good"

algoth1 — Mon, 27 Apr 2026 13:30:50 +0000

Will we finally have a native way to ‘select all’ text in iPadOs?

New comment by algoth1 in "What's Missing in the 'Agentic' Story"

algoth1 — Sat, 25 Apr 2026 17:20:20 +0000

Open Office on Ubuntu 11.10 user here. I can confirm it froze frequently and you would lose everything. it was incredibly frustrating

New comment by algoth1 in "What's Missing in the 'Agentic' Story"

algoth1 — Sat, 25 Apr 2026 17:15:33 +0000

Manually editing config files thanks to an obscure thread so that your printer can actually be recognized by the OS

New comment by algoth1 in "I cancelled Claude: Token issues, declining quality, and poor support"

algoth1 — Fri, 24 Apr 2026 16:50:21 +0000

Doesn't "poor support" implies that there is some sort of support? Shouldnt it be "no support"

New comment by algoth1 in "GPT-5.5"

algoth1 — Fri, 24 Apr 2026 00:34:10 +0000

Same here

New comment by algoth1 in "Our eighth generation TPUs: two chips for the agentic era"

algoth1 — Wed, 22 Apr 2026 18:56:53 +0000

Aistudio should be their default app

New comment by algoth1 in "Banned by Anthropic"

algoth1 — Sun, 19 Apr 2026 22:59:44 +0000

You can file a report through HackerOne: https://hackerone.com/anthropic-vdp?type=team file it as a bug (which it is)

New comment by algoth1 in "Claude Opus 4.7"

algoth1 — Fri, 17 Apr 2026 11:21:29 +0000

On the leaked codebase they show 100+ messages that are randomly cycled through

New comment by algoth1 in "Claude Opus 4.7"

algoth1 — Fri, 17 Apr 2026 11:03:07 +0000

I suspect this is part of the reason why gemini 3.1 pro is insanely good on AiStudio and pretty bad on the gemini app. I have thousands of small videos to convert to detailed descriptions and I'm using a super detailed system prompt. It works perfect either via api or Aistudio. I tried doing a gem on the gemini app using the same prompt as the gem instructions and I just can't get the same results. So, the issue might be not just the rlhl but also the massive system prompts injected on the app interface

New comment by algoth1 in "Fix monitor that goes black, off or blinks due to static electricity in chair"

algoth1 — Wed, 15 Apr 2026 19:17:57 +0000

Many years ago I had a LG CRT that often would turn off in the exact moment I entered the bedroom. The monitor was configured to go to sleep after 20 or so minutes of inactivity, so it was supposed to turn off on its own. And I always assumed it was a case of only noticing it when it did happen (like when you buy a car and suddenly start seeing the same model everywhere)... But it always seemed uncannily frequent... Now I wonder if I might have somehow disturbed the electric field each time

New comment by algoth1 in "Stanford report highlights growing disconnect between AI insiders and everyone"

algoth1 — Tue, 14 Apr 2026 01:20:57 +0000

My wife has a very serious health issue, that has caused more suffering then words could describe. o1-preview was the first ai that actually proved useful. From there on, each improvement on ai caused an incremental improvement in her situation. Even recently we were able to pinpoint exactly what was causing her flare, and solve the situation the same day, just by prompting a claude opus conversation where i’ve shared all her health notes. But if i weren’t a data freak and haven’t been collecting data about her issues (what she does/takes and how she feels) for so long i dont think we would had been able to get this far. So i think ai appeals to people with problems that can be solved by finding patterns in data. People that say ai makes mistakes don’t understand that the power is in finding patterns, not in finding THE right answer. You need to prompt from that prespective

New comment by algoth1 in "Categorization Is 'Baked' into the Brain"

algoth1 — Mon, 13 Apr 2026 15:04:10 +0000

Autistic brains categorize when given enough examples

New comment by algoth1 in "Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage"

algoth1 — Sun, 12 Apr 2026 14:04:37 +0000

Wasn't Antrophic previously offering double the token usage outside busy hours? Now they are counting tokens back at normal rate. But yeah, it's not good. I use codex because claude insists in peaking at and messing with folders and file outside its work area though

New comment by algoth1 in "Web Augmenter – Reshape any website with one sentence"

algoth1 — Mon, 06 Apr 2026 17:32:22 +0000

I think a cool use would be as an harness for agents or automation workflows, to simplify the page/remove clutter to facilitate navigation. I.e. have the agent send commands to your tool

New comment by algoth1 in "Show HN: I built a tiny LLM to demystify how language models work"

algoth1 — Mon, 06 Apr 2026 16:51:27 +0000

I think you could probably feed a copy of a toki pona grammar book to a big model, and have it produce ‘infinite’ training data

New comment by algoth1 in "Show HN: I built a tiny LLM to demystify how language models work"

algoth1 — Mon, 06 Apr 2026 11:54:03 +0000

This really makes me think if it would be feasible to make an llm trained exclusively on toki pona (https://en.wikipedia.org/wiki/Toki_Pona)

New comment by algoth1 in "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs"

algoth1 — Wed, 01 Apr 2026 09:09:19 +0000

Does asking it to think step by step, or character by character, improves the answer? It might be a tokenization+unawareness of its own tokenization shortcomings

New comment by algoth1 in "Entso-E final report on Iberian 2025 blackout"

algoth1 — Fri, 20 Mar 2026 13:00:14 +0000

As someone who lived through the blackout it was wild. I felt back into the pre-internet, pre-smartphone era. It was pretty cool actually. The rumor mill spread so fast that Within hours the official word on the street was that we were getting hacked by a foreign military and people were joking that we had nothing of interest to be conquered xD