ChatGPT is now superhuman at one specific annoying thing – searching Gmail. GPT-5.5 is got a LOT better & quicker. I honestly hate searching on gmail by hand, for a search company their gmail search is surprisingly awful.
@petergostev
-
Wife Banned AI Talk Before Wedding, Missed o3 Launch
By
–
My wife banned me from talking about AI in weeks coming up to our wedding, and thus is when o3 was coming out. She missed out on a lot of hot takes
-
Image Processing Limitations in AI Background Removal Models
By
–
I don't think it's anything to do with the underlying model, it is an extra step that they do to process the image with a background remover model, which looks like they haven't prioritised just now. The model itself can't just generate transparent pixels
-
Claude Opus 47 Context Worlds: Hosted Generations on GitHub
By
–
Hosted generations: https://
petergpt.github.io/claude-opus-47
-context-worlds/
… GitHub: https://
github.com/petergpt/claud
e-opus-47-context-worlds
… -
Opus 4.7 Context Window: 400k vs 1m Performance Analysis
By
–
Opus 4.7 – 400k vs 1m context – is there a difference?
— Peter Gostev (@petergostev) 28 avril 2026
I've heard @theo talk about the fact that it is unlikely that Anthropic would have offered up a model with 1m context at the same cost, if it wasn't a different (i.e. cheaper to serve) model.
I did a test where I toggled… pic.twitter.com/tQC4Tn17elOpus 4.7 – 400k vs 1m context – is there a difference? I've heard @theo talk about the fact that it is unlikely that Anthropic would have offered up a model with 1m context at the same cost, if it wasn't a different (i.e. cheaper to serve) model. I did a test where I toggled
-
Running OpenAI 4o and o4 models simultaneously
By
–
I never complain! The peak was when we had 4o and o4 at the same time
-
Codex-Max Controversy: What Happened and Why It Matters
By
–
Are we going to pretend like the while 'Codex-Max' thing never happened?
-
Improving Image Generation Parallelization and Resolution in Codex
By
–
I'd appreciate if you could improve the way images are done in Codex – there seems to be 1) no parallelisation, 2) don't think I can go to 4k, 3) there is something funny sometimes with how Codex sees the generated images, whether they are getting properly passed into the
-
GPT-5.5 Coding Capabilities Better Than Rankings Suggest
By
–
Yeah totally, I agree gpt-5.5 is way better at coding that this ranking suggests, we'll do better & we'll have a better way to measure more broad coding ability too. Appreciate the feedback
-
Bullshit Benchmark: Evaluating AI Model Reliability
By
–
GitHub: https://
github.com/petergpt/bulls
hit-benchmark
… DataViewer: https://
petergpt.github.io/bullshit-bench
mark/viewer/index.v2.html
…