claude code's full screen renderer is horrible.
- unexpected clicks turning into clicks (accept a decision while reading through the plan)
- laggy while scrolling huge sessions
- consumed more CPU than usual session
@thsottiaux i've felt after the manual reset the limits are draining so fast..
did a manual reset yesterday and already consumed 35% of my weekly usage.. strange
opus 4.8 feels soo dumb rn
- keeps on forgetting mid session
- doesn't follow the instruction
- keeps inventing stuff without actually reading the code ( too lazy)
@claudeai bring back fable!!
@thsottiaux i've felt after the manual reset the limits are draining so fast..
did a manual reset yesterday and already consumed 35% of my weekly usage.. strange
built a tracer viz!!
i've been tokenmaxxxing a lot recently with codex and claude and sometimes i wanted to see in-depth analytics of all the sessions and tokens spent per request.
wanted to see which harness performs better, but coudln't find a decent tracer viewer..
anyone built a reliable system/solution for indexing and searching threads across claude code, codex, cursor..etc? All the built-in ones are not that great.
You switch between Claude Code, Codex, Cursor… and forget where you did what.
> tracebench v0.4 adds search across all of them, by what you actually said and did inside a thread, not just titles.
> "find the thread where we fixed the auth bug" → shows up the relevant threads related to it.
very useful if you are dangling around with all these coding agents
npx tracebench -- just a simple command to view all your sessions in a single window
https://t.co/o9ezTZpScV
You switch between Claude Code, Codex, Cursor… and forget where you did what.
> tracebench v0.4 adds search across all of them, by what you actually said and did inside a thread, not just titles.
> "find the thread where we fixed the auth bug" → shows up the relevant threads related to it.
very useful if you are dangling around with all these coding agents
npx tracebench -- just a simple command to view all your sessions in a single window
https://t.co/o9ezTZpScV
shipping 🔥0.3.0–0.3.1
> now shows you what's eating your context window -not just what it cost.
> four harnesses, each session has context tab jump to that moment on the timeline. 80% line when you are about to get compacted
npx tracebench
https://t.co/uoIjisnF8O
SpaceX has exercised the option to acquire @cursor_ai in an all-stock transaction with the goal of building the world’s most useful AI models.
For the past few months, SpaceXAI has been jointly training a model with Cursor, which will be released in Cursor and Grok Build soon.
We look forward to working closely with the Cursor team to advance our frontier AI capabilities
shipping 🔥0.3.0–0.3.1
> now shows you what's eating your context window -not just what it cost.
> four harnesses, each session has context tab jump to that moment on the timeline. 80% line when you are about to get compacted
npx tracebench
https://t.co/uoIjisnF8O