robertwt7

it seems like 5.6 SOL is better at almost everything than Mythos except Coding Benchmarks (except TerminalBench)? anyone knows why Mythos scores so high on SWEBench are they cheating or are they just optimised better for coding?

at this point I might just try Neuralwatt and see how much request I can get with GLM5.2. I've read a lot of reviews that its very cheap to run using Neuralwatt cloud

what is that moodboard and chart of hypertension in the middle of the article that isn't explained?

This is a great step up in open models however the pricing to support z.ai is not far cheaper than Claude / OpenAI subscription

I built an offline background remover website that now includes passport photo editor, object remover, image compressor. everything is free and offline (inferred from WebGPU) and I used to have to browse to different website to do all of these. now i can just do it offline on my own site.

https://bgremovefree.com/

private trackers are the only way to go nowadays I think. I've stopped using TPB for 11 years now since I joined private trackers. safer, less dead torrents, higher quality

Gpt 5.5 combined with codex is really good. I actually have no doubt whenever I asked questions, plan, or implement a code with it. With opus 4.7, I have to keep double checking because it doesnt follow the CLAUDE.md instruction, it hallucinates a lot, by default it makes things up when it can’t find the answer to something. Its crazy how quickly people are saying that OpenAI is left behind last year when they declared code red and look at where we are now

yeah this is crazy we had many PRs reverted as well on many repos. downtime is 1 thing, but reverting PRs is failure on another level

I actually did the same pilot for a couple of days, while I don't like codex reply, it tackled some problems that claude were spinning for 20 minutes in 5 minutes. Now I have them side by side for codex to review claude's plan and it always find something that claude missed. The reply and the format though is not as good as claude. Pros and cons really, there are many cases where claude weren't able to debug prod issues like codex did as well for me

I always try out new photo editors but I've kept coming back to LR because of familiarity + number of presets / plugin (Dehancer) that I've bought. I think there should be some presets converter somewhere that helps us with moving to other software, not much can be done for plugin though. regardless I'm a happy user of Davinci Resolve and this is amazing!

I really really like tmux, probably i'll try Zellij at some point but its always my default on a new server to install tmux, copy oh my tmux and vimrc configs. then voila I have everything. I have to say I feel magical most of the time i'm using it

There’s a startup callled Graphite dedicated to stacked PRs. I have been using them for a while now I always wonder why github doesn’t implement something similar to this. I probaly will try and switch to GitHub to see if it works flawlessly

How did they agree to the terms that were initially put forward by Anthropic but with OpenAI? Surely there’s a catch here. Or is it just Sam negotiation skill?

I’m surprised that gemini 3 pro is so low at 31.1% though compared to opus 4.6 and gpt 5.2. This is a great achievement but its only available to ultra subscribers unfortunately

yeah this should be the standard, same here in Australia unfortunately the police will just pretend to care by taking more information and then does nothing.

I always find some things that doesn't work with my PC on windows 11. Sometimes things as simple as moving files in explorer makes it hangs where I had to restart explorer.exe. This is embarrassing really that windows can't get this right. There are so many times where I was frustrated and wished that I can just use my macbook pro as my only workstation. I just wish that steam on linux has full support for most games that are it supports in windows then i'll make the switch

my pc is not even that old, its ryzen 9 5900x with rtx 3080 and 32gb ram. however it is sluggish compared to my m1 pro macbook pro

yeah this is so sad, I'm an early supporter of Tailwind since v1 and I also bought the tailwind UI as well to support them. I hope this era doesn't discourage the tailwind team or put them out of business

Congrats for this! how does this differs from claude-mem? I've been using claude-mem for a while now

https://github.com/thedotmack/claude-mem

Merry Christmas everyone!!

looking at the results, it seems like flash should be the default now when using Gemini? the difference between flash thinking and pro thinking is not noticeable anymore, not to mention the speed increase from flash! The only noticeable one is MRCR (long context) benchmark which tbh I also found it to be pretty bad in gemini 3 preview since launching

this is very impressive! as much as I love Claude though, is it just me or their limit is much lower compared to others (Gemini and GPT)? At the moment I'm subscribed to Google One AI ($20) which gives me the most value with the 2tb google drive and Cursor ($20). I've subscribed to GPT and Claude as well in the past, I find that I was hitting the limit much faster in Claude compared to all the others, it made me reluctant to subscribe again. from the blog post it seems like they've been prioritising the Max users most of the time?

yeah i agree, the prompt is to "shorten the giraffe's neck length", not to bent it. i feel like the Gemini 3 produces better result on that one

this should affect a lot sites? I'm trying to access tailwindcss and I can't as well!

as much as I love Wikipedia and I think we need it, I just realise that I haven't opened Wikipedia in the past few months. My default workflow is now replaced to Option + Space and ask gpt questions.

This is very similar to Jules by Google! https://jules.google/

Although I wish that the performance of Jules is worse than Gemini CLI. I hope that this is as good as the Claude Code CLI.

This is crazy. Healthy debate and disagreement should be free in a democratic country, without any fear of violence, let alone death.

I am Australian, the state that we have become is just sad. The fact that this is brought under the disguise of "child protection" is ridiculous and I never would have imagine a future in my own country where I have to submit my ID to access anything online. They will never achieve anything with this because everyone will just use VPN. It's costing taxpayer's money without any useful outcome. The level of incompetence displayed by this government is astonishing.

This will be similar to Typescript I assume? If so I can’t wait to use it!! I cant count how many times I’ve searched for “TS like in Python” since I’ve started working on Python codebase. TS is so awesome that I use it 100% on new projects. Ruff is also very good, but with this, large code base Python will be a breeze to work with

I agree with the process not saving any of our time. however aren't examples supposed to be simple?

Take it from Aider example: https://github.com/Aider-AI/aider It asked to add a param and typing to a function. Would that save us more time? I don't think so. but it's a good peek of what it can do

just like any other hello world example i suppose

so much love for tailwind! I've used it since version 1 and have been always my default for starting new projects.

Congrats to tailwind team!

Hi Peter! Thanks for doing this! I've been watching this thread and reading for so many times but now I have a question.

If I come from Australia with an E3 visa, what is the pathway for me to get a greencard? On the US Gov website, the E3 visa is a non-immigrant visa. does this mean that I can't convert to H1B or greencard if I came with E3 visa?

Thankyou