ivanbokii Profile Banner
Ivan Profile
Ivan

@ivanbokii

Followers
264
Following
12K
Media
43
Statuses
3K

Software Engineer. Interested in system design and hammock-driven development. Edinburgh walker.

Edinburgh, Scotland
Joined December 2008
Don't wanna be here? Send us removal request.
@ivanbokii
Ivan
7 months
ugh, forgot to mention that I'm referring to Claude Code and not the web interface
0
0
0
@ivanbokii
Ivan
7 months
Hey @AnthropicAI folks, I’m on $100 Claude subscription, and I just started my 5hour window but already seeing “Claude Opus 4 limit reached, now using Sonnet 4.” Had a similar experience yesterday. I understand that Opus 4 counts 5x in terms of consumption, but it’s clearly off.
1
0
0
@karpathy
Andrej Karpathy
11 months
I don't have too too much to add on top of this earlier post on V3 and I think it applies to R1 too (which is the more recent, thinking equivalent). I will say that Deep Learning has a legendary ravenous appetite for compute, like no other algorithm that has ever been developed
@karpathy
Andrej Karpathy
1 year
DeepSeek (Chinese AI co) making it look easy today with an open weights release of a frontier-grade LLM trained on a joke of a budget (2048 GPUs for 2 months, $6M). For reference, this level of capability is supposed to require clusters of closer to 16K GPUs, the ones being
370
2K
14K
@gonzalo_io
Gonzalo Cordova
1 year
Been diving into some great AI/ML blogs lately: - Blog by @chipro - Blog by @eugeneyan (links below) I'm curious to find new gems. What are you reading these days?
4
3
19
@kachayev
Oleksii Kachaiev 🇺🇦
1 year
That’s a true masterclass in russian imperialism, when you seamlessly believe that Ukrainians have to forgive russians in the name of some (imaginary) love, all while struggling to understand why Ukrainians keep fighting so fiercely to protect home and families they actually love
0
3
9
@YearsProgress
Year Progress
1 year
2025 is 0% complete.
356
12K
91K
@jeremyphoward
Jeremy Howard
1 year
The inspiration from @ncooper57 to get tmux to do the heavy lifting to make ShellSage work is genius! Thanks to this, ShellSage is <100 lines of code (plus comments and prompts). But the result is amazing. Try it out and tell us how you go. Details here: https://t.co/fdEtttNbyM
Tweet card summary image
answer.ai
ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly
5
7
83
@samwhoo
Sam Rose
1 year
If you haven’t tried Atuin yet, you should! Has become a daily-use tool for me in the last couple of years.
0
1
6
@worrydream
Bret Victor
1 year
★ Dynamicland's new website documents ten years of progress toward a humane dynamic medium.
Tweet card summary image
dynamicland.org
Incubating a humane dynamic medium.
23
200
828
@mytechceoo
Jason
1 year
Founder Mode is now streaming on @netflix
105
268
3K
@criccomini
Chris
1 year
Big news: I'm helping with @martinkl with a second edition of Designing Data-Intensive Applications! An early release of the first 3 chapters is now available (O'Reilly Learning subscribers only at this point) and we're hoping to finish it next year. https://t.co/SpDUBCLdLi
Tweet card summary image
oreilly.com
Data is at the center of many challenges in system design today. Difficult issues such as scalability, consistency, reliability, efficiency, and maintainability need to be resolved.... - Selection...
10
34
192
@mariaKhalusova
Maria Khalusova
1 year
I want @cursor_ai but in @pycharm . I keep switching between the two!
1
1
5
@sarah_edo
Sarah Drasner
2 years
So, um, I’m not sure how to say this but… the movie Her was *supposed* to be dystopian, not aspirational https://t.co/QSwMvGt7lJ
Tweet card summary image
thewrap.com
Scarlett Johansson was "shocked" after ChatGPT created an AI voice that sounded "eerily" like her after she declined to voice it herself
99
292
3K
@jasonfried
Jason Fried
2 years
Very clear thinking from @destraynor here. Nice presentation too. Moody future without sensationalism. Obviously smart marketing too. Intercom is re-rooting itself in very fertile soil, in the perfect weather.
@eoghan
Eoghan McCabe
2 years
Welcome to Off Script! In episode 1, @destraynor shares some poignant and emotive ideas to help us understand the great importance of this time in tech, some stories about our internal reaction to the dawn of modern AI, and some frameworks for how you can respond too. Enjoy.
6
9
156
@ivanbokii
Ivan
2 years
@AnthropicAI hello dear Anthropic, can you please reinstate my account 🙏. Also, would be really good to know how likely using DSPy's ideas on automatic prompt eng. can lead to a ban.
1
0
0
@ivanbokii
Ivan
2 years
Was very proud of building a custom retriever based on Claude Haiku while playing with DSPy, and then got a ban from Anthropic for potential model scraping. 🤦‍♂️
1
0
0
@rickyfm
Ricky
2 years
I’m not worried, I’ll just invite Devin to all my meetings so it can’t get anything done either
22
135
2K
@Mij_Europe
Mujtaba Rahman
2 years
.@radeksikorski on 🔥. The kind of diplomacy I can get behind. Everyone should watch this clip today https://t.co/Zl1NrlxHqQ
232
3K
9K
@pli_cachete
Rota
2 years
If they made those little baby bouncers for adults and attached a desk they would pull in so much money from the software engineering crowd
51
192
4K
@afterveil
afterveil
2 years
i'm so ready for the education, entertainment AI revolution 🤣🌠
101
550
4K