Hacker News: _345

New comment by _345 in "OpenLogi"

_345 — Wed, 19 Aug 2026 04:38:03 +0000

Isn't it wasteful to have everyone go off and remake the same software with slightly different bugs in it instead of one that fixes almost all of the bugs

New comment by _345 in "OpenLogi"

_345 — Wed, 19 Aug 2026 04:36:22 +0000

Yeah even if the software is good there's just something sad about realizing you're reading AI generated text. Even if its proofread and factually correct it just comes across as cheap and low effort, moreso when the content gets duplicated in a pointless FAQ that just restates everything you just read

New comment by _345 in "GPT-5.6 Sol Pricing Cut by 50%"

_345 — Tue, 18 Aug 2026 03:15:20 +0000

Yes I filed a support ticket with them and explained that their system is broken and they just did not care. I explained how it was impossible for me to use it 3 times already as I've only made 2 chatgpt accounts EVER, and only recalling entering my phone number for one of the two chatgpt accounts. I told them that this issue locked me out of codex and chatgpt for work and they weren't willing to do anything about it. Totally useless support.

I ended up borrowing my gf's phone number just so I could get access for work. Ridiculous

New comment by _345 in "Accelerating GPT-5.6 Sol Ultrafast"

_345 — Fri, 14 Aug 2026 05:42:10 +0000

Hope to be a part of this someday...

New comment by _345 in "Would you get tattooed just to interview at a 7-days-a-week AI startup?"

_345 — Fri, 31 Jul 2026 20:56:44 +0000

I'm pretty sure the lemon lime game referred to in the article is supposed to be some trick where it always says you're wrong and you have to cheat (maybe in browser developer tools) to get a 7/7

New comment by _345 in "A $500 RL fine-tune of a 9B open model beat frontier models on catalog review"

_345 — Tue, 28 Jul 2026 04:05:12 +0000

"87.3%

Share of the maximum achievable score our GRPO-trained 9B open-source model reached on catalog review, vs 76.9% for the best frontier configuration: a 13.5% relative improvement over the frontier, and 36% over its own untrained base (64.2%). The five frontier models, even with optimized prompts, plateaued within a tenth of a point of each other; the trained specialist cleared that ceiling."

_______

This is hard for me to believe. I have a lot of skepticism that frontier models like GPT 5.5 that are likely 2T+ parameters in size only got about 12% more accurate than an untrained 9b parameter LLM.

New comment by _345 in "IceCream – Never use print() to debug again"

_345 — Mon, 20 Jul 2026 04:44:02 +0000

i got half way through the readme for this project and had the same thought and got sad and just left the page

New comment by _345 in "OnePlus halts operations in USA and Europe"

_345 — Thu, 16 Jul 2026 13:35:11 +0000

The oneplus open (2023) is such a great phone, what a shame

New comment by _345 in "Brainless: Shadcn components that look like Claude Code, Codex and Grok"

_345 — Wed, 15 Jul 2026 22:28:35 +0000

What inspired you to make this?

New comment by _345 in "Show HN: Earth Game – An offline CLI for turning life goals into quests"

_345 — Sat, 11 Jul 2026 22:32:51 +0000

i dont understand why you would use this. i think it needs more examples

New comment by _345 in "GPT-5.6 Sol Ultra will be in Codex"

_345 — Mon, 06 Jul 2026 21:36:22 +0000

I feel like its only useful if the work you are doing doesn't have correctness as a high priority. If your work is okay with something only mostly being correct and it can just be slopped together over time then yes throw 500 agents at it. But otherwise you can't really review all that work as a single human and will quickly run out of capacity

New comment by _345 in "Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers"

_345 — Thu, 02 Jul 2026 05:15:33 +0000

This makes so much sense as to why I've always felt that Opus 4.8 was leagues ahead of GPT 5.5. It's so good at taking underspecified requirements and filling in the gaps with sensible approaches for your project

New comment by _345 in "My Steam Machine is a 50ft HDMI cable"

_345 — Fri, 26 Jun 2026 23:03:20 +0000

I did the same thing but it's 25 feet hahaha, love to see this

New comment by _345 in "Reading for pleasure is sharply down among schoolkids, report shows"

_345 — Sat, 13 Jun 2026 06:14:49 +0000

Just you as an adult. It's always been that infantile

New comment by _345 in "[dead]"

_345 — Sat, 13 Jun 2026 05:18:21 +0000

any guesses how?

New comment by _345 in "Claude Fable is relentlessly proactive"

_345 — Fri, 12 Jun 2026 13:22:44 +0000

I'm not letting Jenna from HR log into my personal machine with access to all of my lifelong data though. I do let my claude bypass permissions though

New comment by _345 in "Claude Fable is relentlessly proactive"

_345 — Fri, 12 Jun 2026 04:24:51 +0000

Best comment in this thread

New comment by _345 in "Claude Fable is relentlessly proactive"

_345 — Fri, 12 Jun 2026 04:10:25 +0000

In my case no, I actually saw worse performance with fable medium and switched back to opus high and xhigh

New comment by _345 in "Claude Fable is relentlessly proactive"

_345 — Fri, 12 Jun 2026 04:05:26 +0000

way worse things can happen than your machine being bricked, if a malicious actor can weaponize an agent to do their bidding

New comment by _345 in "Google is finally killing uBlock Origin in Chrome for good"

_345 — Thu, 11 Jun 2026 20:41:18 +0000

I moved to Firefox as soon as they began threatening uBlock Origin support and people started switching to Lite, I find it silly that people were tweaking their registries just to stay on a sinking ship for a few more months lol.