Well the problem you have now is that there are too many features, they conflict together, files get mixed up with the various reviewing tools, options, now worktrees applying stuff back. I'd actually remove features, make only a core set of things that work reliably together.
@alexjc
-
LLM Performance Degradation at 100K Tokens Context
By
–
People working on basic code and reset their Agent chats every 4-5 replies I envy you. Having to work on deep context design work and at about 100k tokens, LLMs start to get lazy / confused. I resorted to giving them codes they have to echo back. They often seem to think
-
Cursor patch reviewing issues with Agent overlapping features
By
–
I will say that Cursor's handling of patch reviewing always feels on the edge of becoming non-functional; so many overlapping features shipped quickly — e.g. if you do things like CMD+K in a file that already has changes by an Agent then it can also blow up…
-
AI Tool Performance Issues and Server-Side Optimization Solutions
By
–
Shows signs of brilliance, faster — maybe it's a problem on the tool side or a simple fix on the serving.
-
Gemini 3 Tool Usage Failures Disappoint in Multiple Languages
By
–
Same problem with patch tool usage in two separate languages and two separate sessions. Companies get one chance to impress these days, and I think Gemini 3 just blew it…
-
Gemini 3 Review: Fast but Practically Unusable
By
–
Gemini 3 review: it's fast, it's not dumb, but it's completely unusable in practice. It will get lost after a few edits then completely trash the file: issuing patch commands that include line numbers at best, and at worst it will discard most of the lines!
-
Tokenizer Approaches Impact LLM Performance on HellaSwag Benchmarks
By
–
If you measure downstream performance on HellaSwag rather than speedrun-equivalent loss, then different tokenizer approaches come out on top… The first run I did was much better on common-sense downstream, trained in equivalent time or better.
-
Tokenizer Training and Data Filtering Compliance Standards
By
–
Well, the tokenizer I used was trained on large quantities of data — I filtered the tokens based on yet more data from FineWeb. Question is if that's acceptable according to your rules…
-
Retokenization and Language Knowledge in Model Training
By
–
The biggest question is whether you allow re-tokenization, and whether that should be done with the same data as the training itself. Right now there is knowledge about the language in existing tokens built-in and changing that is against the rules and/or unfavorable.
-
Plaintiff Lawyers Mishandle Copyright Claims and Cloud Data Evidence
By
–
The plaintiff lawyers mis-pleaded the important Copyright claims, had to withdraw them. They also "forgot" to provide the most damning evidence for reputational harm. I talked to the legal team they had no clue about cloud copies of data even the day before court. I'm not saying