Developing Dosu github.com/devstein
Based in United States
- Tweets 718
- Following 1,237
- Followers 726
- Likes 489
It's Dosu Drop Day! 🎒 For our back-to-school edition, Dosu does the studying. When a Claude Code, Codex, or Cursor session ends, Dosu reads it and writes down what your team would otherwise rediscover. 🧵 go.dosu.dev/drop-sep26-x
2
3
6
356
Devin Stein retweeted
I've frequently seen search use cases that need a vocabulary modeled hierarchically in a taxonomy, and almost never one that needed an actual knowledge graph.
1
1
9
605
I used to be a diehard plan mode-er, but have moved to planning with artifacts and it works just as well
27
The team keeps working after the agent’s session ends.
@devstein64 on how merged PRs and resolved conversations keep agent memory current.
Recording + transcript: dosu.dev/webinars/agent-memo…
1
2
12
202
Devin Stein retweeted
🪦 Security by obscurity
1945–2026
Beloved by developers. Killed by agents.
1
2
22
2,786
it is true
Is it just me or are existing agent memory datasets underwhelming?
They to some extend assume retrieval will just work, they tell you roughly where the right answer is, and then they sit back and see if you can piece together a response.
This doesn't resemble what the work feels like in my experience...
1
3
414
Devin Stein retweeted
Is it just me or are existing agent memory datasets underwhelming?
They to some extend assume retrieval will just work, they tell you roughly where the right answer is, and then they sit back and see if you can piece together a response.
This doesn't resemble what the work feels like in my experience...
5
1
15
1,248
A summary of a summary keeps getting further from the source.
Michael Mangus, Head of Product at Dosu, explains how repeated summaries lose details in agent memory.
Recording + transcript: dosu.dev/webinars/agent-memo…
1
2
5
123
jev may have unseated @cohere as the best reranker across speed, cost, and performance
3
16
1,055
what development looks like when tokens are free
Here's what OpenAI's agentic software factory looks like, today.
Details: newsletter.pragmaticengineer…
(thanks to all the OpenAI folks who explained how it works! And Perf Factory looks especially interesting to me)
3
6
87
8,309
