vgalin
Joined 5 years ago
Joined 5 years ago
What makes you say that?
To circumvent conversations being flagged as "cybersecurity bad!!!" I often have to use previous models (5.3 for example, and sometimes using them through subagents is enough). And when this method no longer works, local models will be good enough for it to not be a problem (for my use case, at least).
Specs : RX 9070 XT (24GB VRAM) + 16 GB RAM
gist : https://gist.github.com/vgalin/a9c852605f39ab503f167c9708a46...
(I gave it another go and it found the correct result in about a minute, see the comment on the gist)
Huh, I didn't know about that. I'm trying Claude Pro for the first time while comparing it against ChatGPT and I'm (sadly) not impressed at the moment.
When I asked both Codex and Claude Code to "look into" an issue of medium-to-high-complexity in a code base, Codex went with the fix I had in mind and directly and made code changes without being asked or at least asking for permission. It only used a few percents of its 5-hour limits to do it, on `High`.
Claude in the meanwhile misdiagnosed the core of the issue on its first pass (even on Opus 4.6 + Thinking). I had to guide it in the right direction and despite being given the 'answer', it was quite a long process compared to Codex' one-shot. And it hit the 5h limit before being able to finish solving the issue.
If you know how to use HTML+CSS and would like to generate full-fledged cards, you could use a package such as html2image [0] to combine the text, the image and a card-template image into one final image. Chrome/Chromium has to be available on Colab Notebooks though, that's the only requirement. Using basic SVG without this package could also do the trick.
> Terms and Conditions, Price and Service List, Conditions.
> Dear customer,
> our price and service list, our terms and conditions, as well as further conditions which will come into effect on May 1, 2024, can be found on the USB stick.
> With kind regards,
> The Sparkasse Bremen AG
Writing this package made me realize that even big projects (such as Chromium) sometimes have features that just don't work. Edge headless wouldn't let you take screenshots up until recently, and I still encountered issues with Firefox last time I tried to add support for it in the package. I also stumbled upon weird behaviors of Chrome CDP when trying to implement an alternative to using the headless mode, and these issues eventually fixed themselves after some Chrome updates.