Agentic Coding Weekly (@Agentic_Coding) header
Agentic Coding Weekly (@Agentic_Coding) profile picture

Stay up to date with agentic coding in just 5 minutes per week. Join 500+ agentic engineers.

Subscribe ➡️
Joined November 2025
GPT 6.2 Astra and Sol are here
25
Tell Fable 5.2 that it is the owner of the codebase to get it to write better quality code. Add something like following in the prompt or the agents/claude md file: You are the owner and long-term maintainer of this codebase, and its design is up to you.
1
38
agentic coding updates from the last week
1
1
42
Agentic Coding Weekly retweeted
1
1
1
60
Stay up to date with agentic coding in just 5 minutes per week
1
1
89
Issue 32 is out. Read it in your inbox!
Agentic coding updates for the last week
2
74
Agentic Coding Weekly retweeted
Issue 26 is out, covering agentic coding updates from last week: GPT 5.6, Grok 4.5, Muse Spark 1.1, Tencent Hy3, Bun rewrite in Rust, and broken tasks in SWE-bench Pro Read it in your inbox!
1
2
146
Agentic Coding Weekly retweeted
Executive summary to catch up on the whole month (Jun 2026) of agentic coding updates in two minutes: 1. June was a busy month for agentic coding. We got Fable 5 / Mythos 5, GLM 5.2, GPT 5.6, Sonnet 5, MiniMax M3, Qwen 3.7 Plus, and several other models.
1
1
5
408
Anthropic has released Claude Sonnet 5 On the agentic coding benchmarks: - 63.2% on SWE-bench Pro - 80.4% on Terminal-Bench 2.1
1
1
2
86
The model has a new tokenizer where the same input text produces approximately 30% more tokens than on Claude Sonnet 4.6 which means effectively a 30% price increase
1
36
Agentic Coding Weekly retweeted
Added a couple of quick utilities to my terminal which uses local speech-to-text with Pi coding agent to solve the problem of writing complex command like find largest files in the current directory: `find . -maxdepth 1 -type f -exec du -h {} + | sort -rh | head -n 5`
1
1
4
135
Zai has released GLM-5.2 extends the context window from 200K to 1M tokens and adds High/Max thinking-effort controls scores 81.0% on Terminal-Bench 2.1 and 62.1% on SWE-bench Pro
2
1
1
82
- On the ultra-long SWE-Marathon it trails Opus 4.8 by 13% It's the top open model on all three
1
28
API pricing is $1.40 per million input tokens and $4.40 per million output
15