Prompt caching didn't even exist until <2 years ago Google: June 2024
Anthropic: August 2024
OpenAI: October 2024 Now for agentic workflows, 95% of tokens gets cached, without it the costs would be completely insane
@petergostev
-
The Impact of Prompt Caching on LLM Agentic Workflows and Costs
By
–
-
Challenges in Enterprise AI Adoption and Employee Usage
By
–
I know CEO-level top down tokenmaxxing is considered dumb, but what are they to do when they've exhausted 'the good way' – you got everyone licenses, did AI workshops, appointed AI champions, did AI hackathons – then you check back and adoption is 25%, of which 80% is tab
-
Voice-first shopping for dino outfits
By
–
I've always wondered why we don't see any voice-first interfaces, so I tried to build one with OpenAI's new realtime voice api – you can now shop for your dino outfits with just your voice. pic.twitter.com/gKFekQ84RN
— Peter Gostev (@petergostev) 10 mai 2026I've always wondered why we don't see any voice-first interfaces, so I tried to build one with OpenAI's new realtime voice api – you can now shop for your dino outfits with just your voice.
-
Even image models fail as world models; video is harder
By
–
Even the image models are not good enough world models yet, gpt-image-2 and nano banana make pretty obvious world model like mistakes. is way harder, so no hope of that anytime soon. Maybe with 2-3 OOMs it gets good enough, but that doesn't feel like a reasonable thing to
-
Demo at OpenAI event London 2025: model trained on UN translators
By
–
Fun fact, I saw a demo of this at an OpenAI event in London in something like October 2025 – over half a year ago. They told us that they trained the model on UN synchronised translators. Not sure why it took so long to release it https://t.co/lwoaaZy7eB
— Peter Gostev (@petergostev) 7 mai 2026Fun fact, I saw a demo of this at an OpenAI event in London in something like October 2025 – over half a year ago. They told us that they trained the model on UN synchronised translators. Not sure why it took so long to release it
-
New live translator model and Chrome extension for YouTube live translation
By
–
The new live translator model is really outstanding – it can translate synchronously without getting confused. This video is just my screen recording with no editing.
— Peter Gostev (@petergostev) 7 mai 2026
I built a little chrome extension that can hook into a YouTube video and translate it automatically live to… https://t.co/ZXa7go1ETV pic.twitter.com/M0RDVWzxRJThe new live translator model is really outstanding – it can translate synchronously without getting confused. This video is just my screen recording with no editing. I built a little chrome extension that can hook into a YouTube video and translate it automatically live to
-
Separate Gemini account from Google to avoid ban risk
By
–
I'd love it if Gemini account was completely separate from a my Google account. Google is so important for my day to day life, and considering how trigger happy AI companies are to ban users, I don't want to get banned from Gmail etc for pushing Gemini a bit too far.
-
Post by @petergostev with GitHub links and data viewer
By
–
GitHub: https://github.com/petergpt/bullshit-benchmark
… Data viewer: https://petergpt.github.io/bullshit-benchmark/viewer/index.v2.html
… -
User Builds Codex Pet With Usage Limit Ring Display
By
–
Got my dog as a Codex pet, but more interestingly got Codex to add the rings to show my Codex limits. Outer ring is 5 hours, inner the weekly one https://t.co/TpkCvj7BdH pic.twitter.com/ypBcdfJZPz
— Peter Gostev (@petergostev) 3 mai 2026Got my dog as a Codex pet, but more interestingly got Codex to add the rings to show my Codex limits. Outer ring is 5 hours, inner the weekly one
-
User Requests Smarter Auto-Compaction Timing for Codex
By
–
Codex suggestion – can you do auto-compaction smartly when I'm not using Codex if I'm close, sending a follow up message to a thread and then immediately hitting auto-compaction is quite annoying