Nathanael (@human_eiffel) header
Nathanael (@human_eiffel) profile picture

Software Developer... Built Kaleidoscope a visual QA software for agents. Working on becoming an AI engineer https://teapawt.net/t.co/EBm6LQ8W5r

Joined April 2020
Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)Photo by Nathanael (@human_eiffel)
Haven't been able to work on this for some time because I had a lot going on, but I'm on it again... Remembered my Fable access expires tomorrow so I decided to get it to make product videos for my software using Remotion. Here's the one for Anchor
Working on an app to help fight procrastination and I can't decide which of these animations to go with (Emil Kowalski's skills really work well for Expo apps).
2
2
4
145
Claude code logged me out mid session, checked and it seems they have an issue over there too... But TEAMS IS STILL WORKING FINE🥲
1
1
176
Seems everyone is mad about it😂😂
Se cayó Outlook y todo el ecosistema de Microsoft 365 excepto el hpta Teams. Es increíble como esa app del demonio es practicamente indestructible.
43
Nathanael retweeted
Microsoft, If you're going to do something, do it well! It should've been Outlook AND teams! Both! You had one job!!!
1
2
631
Microsoft, If you're going to do something, do it well! It should've been Outlook AND teams! Both! You had one job!!!
1
2
631
Nathanael retweeted
Photographer captures iguana that looks like Godzilla 🦎 📷: @dale_r_morris
605
8,589
1,518
100,180
8,726,113
Bookmarked too... I am a very patient man🙂
🤷‍♂️ The whole Chelsea squad wanted his shirt. Who can blame them? You can get yours for 20% off: shorturl.at/rKwOn 🛍️
1
68
Nathanael retweeted
Symmetry...
Newbies trying to grow in the age of AI... Shots are of a sweetsop tree (custard apple family)
2
1
91
Symmetry...
Newbies trying to grow in the age of AI... Shots are of a sweetsop tree (custard apple family)
2
1
91
You broke a Rupert drop???? Nah man, gotta be hulk or something
87
Nathanael retweeted
I can't wait for OpenAI to fix their model
13
2
22
2,131
Nathanael retweeted
Was looking at moving my AI engineering side project from GPT to Claude and pasted the project instructions in Claude... This thing saw 'Hit Rate@1 80%' and I kid you not, it gave me a suicide prevention hotline and told me to call if I'm having a difficult time😂...
3
1
2
58
Was looking at moving my AI engineering side project from GPT to Claude and pasted the project instructions in Claude... This thing saw 'Hit Rate@1 80%' and I kid you not, it gave me a suicide prevention hotline and told me to call if I'm having a difficult time😂...
3
1
2
58
Nathanael retweeted
Switched from Codex to Claude Code on the same $20 plan, and I'm genuinely blown away. I've been using Codex for a while, but recently decided to give Claude Code a shot. Same $20/month, but the difference feels massive. It genuinely feels like I'm using AI from a year in the future. I was expecting Claude to burn through my quota pretty quickly, especially with Opus 5.5. But surprisingly, I'm struggling to even exhaust it. Here's a real example: I gave Sol 6.1 a Figma design to implement, including proper testing across the specified breakpoints. It burned through the entire 5-hour quota and only managed to complete around 70% of the work. Then I tried the same task with Opus 5.5 on medium effort. It completed the whole thing, delivered noticeably better quality, and used only about 50% of my 5-hour quota. I'm genuinely confused. Did Anthropic accidentally give me the Max plan or something? Because this is ridiculous. I know it's just one comparison, but the difference in my experience has been insane. To all the Codex users: seriously, give Claude Code a try. You might be surprised how far behind you've been feeling without even realizing it.
92
14
4
477
71,910
Nathanael retweeted
Favorite feeling in open source: You build a thing. Years pass. It hits 9K stars at @infinite_red and doesn't need you anymore. That's success. 🫡 github.com/infinitered/nsfwj…
2
1
16
1,251
Ohhh this cracked Atlassian engineer... W
I am pleased to announce that I've accepted an offer to work as a Staff Software Engineer, on the Traffic Engineering team @ Tesla, where I'll be working on control-planes and edge networks, as nature intended
48
Finally paid for a Claude sub after weeks of hoping OAI would come through. Used Opus 5.5 for two hours and I get it now... I really do... TPS is nowhere near Sol 6.1, much faster Smarter in so many little ways Sol isn't Better suggestions and followups Better token usage...
1
2
54
I use the GPT projects feature to learn new stuff, having it guide me through my learning process. It worked because I could do this without worrying about Codex limits but now?😂.
Confirmed: ChatGPT and Codex will share one usage limit from December. OpenAI's help page, updated today: - Plus, Pro and Business get one allowance across ChatGPT and Codex - Usage is measured in tokens, so bigger models and harder tasks burn more - Instant chat doesn't count against it - Combined remaining usage and reset times will show in Settings > Usage - Hit the cap and you wait, upgrade, or buy credits OpenAI says most users won't hit resets more often than now. If you run long Codex sessions and lean on ChatGPT too, plan for both drawing from the same pool. Fair ask to OpenAI: publish the token allowance per plan before December so people can check the maths. help.openai.com/en/articles/…
2
4
183
Errrr lol????
Confirmed: ChatGPT and Codex will share one usage limit from December. OpenAI's help page, updated today: - Plus, Pro and Business get one allowance across ChatGPT and Codex - Usage is measured in tokens, so bigger models and harder tasks burn more - Instant chat doesn't count against it - Combined remaining usage and reset times will show in Settings > Usage - Hit the cap and you wait, upgrade, or buy credits OpenAI says most users won't hit resets more often than now. If you run long Codex sessions and lean on ChatGPT too, plan for both drawing from the same pool. Fair ask to OpenAI: publish the token allowance per plan before December so people can check the maths. help.openai.com/en/articles/…
40