Sent out the latest edition of my newsletter, aka everything I've written on my blog in the past 7 days copied-and-pasted into an email https://
simonw.substack.com/p/gpt-5-key-ch
aracteristics-pricing
…
LLMS
-
GPT-5 Key Characteristics and Pricing Analysis
By
–
-
OpenAI Removes GPT-4o Access Alongside GPT-5 Launch
By
–
One of the surprises for me from the GPT-5 launch yesterday is how OpenAI removed access to older models (like GPT-4o) for most ChatGPT users at the same time as they rolled out the new model. I wrote about how that's been playing out here:
-
GPT-5 Pro outperforms competitors in advanced simulations
By
–
GPT-5 Pro is genuinely a top tier model, it is the best. I know some GPT-5 reactions have been mixed (including from me), but OpenAI has made great strides with Pro. I have made 12 simulations that no other model would match, not from OpenAI, Google, xAI or Anthropic. All of them… pic.twitter.com/vzFKUttbeW
— Peter Gostev (@petergostev) 8 août 2025GPT-5 Pro is genuinely a top tier model, it is the best. I know some GPT-5 reactions have been mixed (including from me), but OpenAI has made great strides with Pro. I have made 12 simulations that no other model would match, not from OpenAI, Google, xAI or Anthropic. All of them
-
GPT-5 Integration Challenges: Agent Harness Optimization Delays
By
–
A lot of folks who are having a bad experience are using GPT-5 in agent harnesses that aren't yet optimized for it. For every new model release, there's a time lag between release + when companies that integrate the model have it truly working well. Agent companies rush to
-
GPT-5 Integration Challenges: Optimization Lag After Model Release
By
–
I think a lot of folks who are having a bad experience are using the model in harnesses that aren't yet optimized for GPT-5. For every new model release, there's a lag time between release + when the companies that integrate the model have it working well. Folks rush to switch
-
GPT-5 Announcement Analysis: Strengths, Weaknesses, Disappointments
By
–
¡NUEVO VÍDEO en el LAB! 24 horas después del anuncio de GPT-5 estas son mis conclusiones de lo presentado ayer por OpenAI. Lo bueno. Lo malo. Y lo decepcionante. Os dejo el link a continuación
-
ChatGPT Interface Optimization for GPT-5 Performance
By
–
Make sure you're using the ChatGPT interface directly. Most of the agent/code harnesses are not optimized for GPT-5 yet, so performance will seem worse than it actually is.
-
Search Speed Data Indexing Chatbots Advancement Feedback
By
–
Instant feedback from these events surfaced what mattered most:
Faster search
Sharper data indexing
Chatbots that just work -
LangChain Enables Citable Search Results with Claude Models
By
–
LangChain supports Claude Opus 4.1 and Sonnet 4’s citable search results — now GA on the Anthropic API and Vertex AI. With this update, you can: • Return search results with built-in titles and source links • Automatically link citations to the tool call that generated them