Now that the API is available, I'm going to be using it through Cline.
@mattshumer_
-
RepoPrompt Enhances ChatGPT Prompt Building and Application
By
–
For testing, I used it directly through the ChatGPT interface. RepoPrompt helped me build prompts + apply changes.
-
Clarity in AI prompts yields exceptional results
By
–
Yes — I've found you need to be super clear with it. If you are, the results are insanely good.
-
GPT-5 Raises the Bar for AI-Powered Software Development
By
–
I've been testing GPT-5 for the last couple of weeks. My biggest takeaway: You can now vibe code *real* software. Not just simple SaaS apps, but real, technical software. This is the best coding model in the world. The ceiling has been raised.
-
GPT-5 Review: Major Leap From Previous Models
By
–
I've had access to GPT-5 since July 21st. Since then, I've used it as my daily-driver, pushing it to its limits. Here's my review of GPT-5 (note: full, interactive review w/ artifacts is linked in the next tweet): — TL;DR: – GPT-5 is clearly a big leap from previous models.
-
GPT-5 Predictions from April 2024: Accuracy Check
By
–
These were my GPT-5 predictions from April 2024… how many do you think I got right?
-
Investors Seek Partnership to Back and Promote Tech Startup
By
–
@JasonKuperberg and I are looking to back something here as well… and hopefully blow them up on X. Would love to partner on finding the right one!
-
RULER: General Purpose Reward Function by OpenPipe AI
By
–
I think you're describing @OpenPipeAI
. Check out their work on RULER (
https://
openpipe.ai/blog/ruler?ref
resh=1754513766765
…), it's essentially a general purpose reward function. Might want to chat with them! -
OpenPipeAI Makes RL Easy for Superhuman MCP Agents
By
–
The @OpenPipeAI team continues to push towards making RL easy. You can now make agents that are superhuman at using specific MCP servers, with essentially zero setup or knowledge.
-
Groq’s Real Value: Token Throughput Over Inference Speed
By
–
IMO this is the big opportunity for Groq, and one of the main reasons I invested. Faster inference is cool, but the real value is going to be in doing more tokens per prompt.