kermitt.bsky.social
@kermitt.bsky.social
The most annoying difference between #Codex and #Claude for me personally is the lack of plan mode. This one small CC feature prevented so many stupid overengineered #AI slop for me 😂
October 3, 2025 at 8:38 AM
In general, I like the concept #OpenAI #Codex introduced: task -> variant -> feedback loop -> pull request. Feels almost like talking to a human through PR review, but there are quite a few things that I don't like: (🧵)
October 1, 2025 at 8:17 AM
What a nice coincidence! #Claude Code 2.0 was released just in time for this experiment. 😎

So far: #Sonnet 4.5 feels good. Some random API errors, I have never seen before, make working with CC feel like working with #Codex 😂

The model is definitely less agreeable now, which is also nice.
September 30, 2025 at 9:35 AM
Trying to work with #AI as if it's a human engineer in a micro project. Quite an interesting challenge: on one hand, the amount of knowledge poured into LLM is stunning, but there's so many issues with “local” context…
September 29, 2025 at 8:27 AM
Reposted
1. Impact. How much revenue does my work protect or generate?

2. Quality. Does my work meet or exceed customer expectations?

3. Efficiency. Reward making the right buy versus build decision.

4. Reusability. How do others leverage my work?

5. Supportability. How much work do I create for others?
a question for the people who write code for money:

if you could wave a magic wand and have your performance/promotability measured on any 5 metrics of your choice, what would those metrics be?
January 23, 2025 at 4:45 PM