HackerTrans
TopNewTrendsCommentsPastAskShowJobs

artursapek

8,158 karmajoined 16 yıl önce
[email protected]

https://art.cx

https://revise.io

Submissions

GPT 5.6 sets new record on proofreading benchmark

twitter.com
1 points·by artursapek·4 saat önce·0 comments

"No, I swear I wrote this."

revise.io
17 points·by artursapek·16 gün önce·46 comments

Which LLM is the best proofreader?

revise.io
1 points·by artursapek·geçen ay·0 comments

Show HN: A fast, free AI rewriter

revise.io
3 points·by artursapek·2 ay önce·1 comments

Spell-Checking with LLMs

revise.io
7 points·by artursapek·2 ay önce·3 comments

Show HN: I benchmarked how good LLMs are at proofreading English

github.com
3 points·by artursapek·3 ay önce·2 comments

GPT 5.5 sets new record in proofreading benchmark

revise.io
3 points·by artursapek·3 ay önce·1 comments

ErrataBench

github.com
2 points·by artursapek·3 ay önce·0 comments

Show HN: ErrataBench - A Proofreading Benchmark for LLMs

revise.io
3 points·by artursapek·3 ay önce·0 comments

Show HN: Revise – An AI Editor for Documents

revise.io
85 points·by artursapek·4 ay önce·76 comments

Show HN: Revise – collaborative documents with LaTeX support

revise.io
1 points·by artursapek·6 ay önce·0 comments

Show HN: Revise – a new canvas-based word processor

revise.io
1 points·by artursapek·6 ay önce·0 comments

Vision Import for PDFs

revise.io
1 points·by artursapek·6 ay önce·3 comments

Show HN: Revise

revise.io
11 points·by artursapek·8 ay önce·1 comments

Show HN: Option trading P&L visualizer

optioncurves.com
2 points·by artursapek·8 ay önce·0 comments

comments

artursapek
·13 gün önce·discuss
I run a proofreading benchmark that tests how well models can find and fix errors in English text. They get several passes in a simple agent loop. Sonnet 5 is definitely better than Sonnet 4.6, but inferior on both quality and cost to GLM 5.1, GLM 5.2, Gemini 3.1 Flash, and Gemini 3.1 Pro. https://revise.io/errata-bench
artursapek
·14 gün önce·discuss
haha yeah I've bet the last 12 months of my career on a .io
artursapek
·14 gün önce·discuss
The .ai TLD is some tiny island with a few thousand people
artursapek
·16 gün önce·discuss
Trivial to simulate basic keystrokes. But I don't think it's trivial to simulate the natural process of drafting something. There's no concrete heuristic or algorithm (yet) for judging these types of replays, but I'd be impressed if someone can actually make a program that reliably simulates a natural keystroke-by-keystroke thought process which appears human when replayed in this way.
artursapek
·17 gün önce·discuss
They claim extreme performance on ExploitBench, which Mythos was touted as being incredible at. https://x.com/OpenAI/status/2070555278576439306
artursapek
·geçen ay·discuss
Fable 5 beats GPT 5.5 in my proofreading benchmark. And it does so at approximately the same total cost; it used significantly fewer turns than 5.5

https://x.com/tmuxvim/status/2064452096800198930
artursapek
·geçen ay·discuss
I would expect Apple to hedge their bet on Gemini and build everything so that the model can be swapped out in the future.
artursapek
·geçen ay·discuss
I use Carplay all the time and I didn't even realize it has voice control. I just set things up on my phone and drive.
artursapek
·geçen ay·discuss
I think it's fair to say that OpenAI has at least partially won the "consumer AI" segment.
artursapek
·geçen ay·discuss
You’re not responding to anything the parent said.
artursapek
·geçen ay·discuss
I agree. I have gotten an incredible amount of work done iterating with 5-30 minute long agent tasks. But it requires I stay engaged, and not go chill on the beach, which I guess is a lot of agentmaxxers’ goal.
artursapek
·geçen ay·discuss
Yeah I don’t really see the backpressure analogy here - it implies that the agent is constantly producing new stuff, which isn’t really possible since the solution is very detailed specs/goals.
artursapek
·2 ay önce·discuss
Salaried people think they get paid for their output. No silly, you get paid for your time. Just like an hourly worker.
artursapek
·2 ay önce·discuss
am I the only one who always replies to people manually? I don't think I've ever done the "send back a chatGPT screenshot" or copy paste a response from chatGPT to a message I know was from a human.
artursapek
·2 ay önce·discuss
A nice reminder to not check the "organ donor" box at the DMV
artursapek
·2 ay önce·discuss
ew the bottom is moldy
artursapek
·2 ay önce·discuss
I'm someone who is trying to build a subscription-based business to cover underlying LLM costs, and very hopeful I can one day just sell a permanent license to the software instead with customers using local LLMs to power it.
artursapek
·2 ay önce·discuss
[flagged]
artursapek
·2 ay önce·discuss
[flagged]
artursapek
·2 ay önce·discuss
Valve practically has a monopoly on PC gaming, I think they're pretty fat and happy too ;D