←
PiG347 posts
PiG avatar

PiG

@PiGCodingAgent

Pi in Go - pi-in-go.dev & github.com/MichaelKinsy/PiG

◷ Joined December 2018▧ 40 Photos and videos
PiG avatar
PiG@PiGCodingAgent·Sep 25

Meet PiG: @pidotdev, rebuilt in Go as one native binary. Live multi-language extensions, derivative harnesses (Piglets), and everything Pi just in Go. More at pi-in-go.dev

1:35
Tanay avatar
⟳ PiG retweeted
Tanay@0xManiac_Man·Nov 12

Happy Birthday Golang, Go pushed to me to learn distributed systems and Infra, i don't like solving leetcode questions but i have solved some of them in go, feels way better than cpp to me over the past 3 months i have also built a repo of all distributed systems patterns written in plain go, entire cncf landscape heavily relies on go because of it's simplicity my first project which i am proud of is connection pool written in go, connection pool can be used to optimise network latency by picking up already warm connections and avoiding tcp/tls handshake + payload ramp every time thanks Go, for everything

Post attachment
Go@golangNov 10

“Go Turns 17” by Austin Clements, for the Go team — go.dev/blog/17years #golang

Larry Yu avatar
⟳ PiG retweeted
Larry Yu@LarryYux·Nov 9

Keep up the work PiG I'm rooting for you 🫵

wolfie avatar
⟳ PiG retweeted
wolfie@wolfie_·Nov 9

I made a continuous isometric cartoon map of sf, based on real apple-maps 3d tiles took ~8 hours with Qwen-Image 2.1 on A100 (2hrs training LoRA + 6hrs generating city) sfiso.wolfie.gg

3:43
zek avatar
⟳ PiG retweeted
zek@zekramu·Nov 9

OPA is surprisingly good and effective at adding another layer of depth to automatic CI checks for your agents. not a lot of people are using it to actually enforce code quality things, but with change detection + AST rules you can get a super fine grained level of depth

dex avatar
⟳ PiG retweeted
dex@dexhorthy·Nov 8

I woke up twice last night thinking “I should do a tweet about how everyone named Can is super cracked” so anyways go follow @can - modal @cansar - codex @can1357 - omp And I’m definitely missing at least one still

wolfie avatar
⟳ PiG retweeted
wolfie@wolfie_·Nov 6

pro tip: don't dogfood near hostile mobs

1:00

gonna build this for omp/tern, hold my beer

Achu Mukundan avatar
⟳ PiG retweeted
Achu Mukundan@achumukundan00·Nov 6

Hi friends! Meet octet. I rebuilt @pidotdev coding agent in Rust, extensible in any programming language. Built for speed, with Pi extension compatibility and optional extensions for codemode, subagents, MCP, and more. free+open source made with ❤️ in Toronto, ON, 🇨🇦

1:19
Bwit avatar
⟳ PiG retweeted
Bwit@BwitneyHouston·Nov 6

Replayed 144 graded subagent runs from my own sessions. Forked vs. briefed fresh subagent: 100% pass rate on both, so no quality gap here. Forking only won on cost while the main session was under 100k tokens. Past that, ~1.3x, even at 90–99% cache hits.

Post attachment

Subagents are the biggest cause of AI failures In most harnesses: 1. Main agent writes a summary of what it knows 2. Subagent starts from that summary only, and makes assumptions 3. Subagent works and sends back a new summary of what it did Same flaw as compaction: all summaries are lossy. This is how your assistant makes emails you never wanted, or purchases what you told it just to get the price of So I tried something new: checkpoint agents The initial agent has complete context of what needs to be done. And that input is already cached Fork the session where it is. Send the fork ahead to do the task and it will do exactly what the main agent would have done; their context is identical What is even better is when the fork finishes, the cache of the main agent is kept warm by the subagent (they share the same prefix) I measured it on a 137k-token session with Opus 5.5: → Main agent does it on its own: 67 s, $0.38, context +8-17k → Checkpoint: 117 s, $0.68, context +2k → Classic subagent: 123 s, $0.57, context +4-5k But here is what I found: avoiding large input is even more important than keeping cache. And most subagent tasks were done better either in series with retrieval, or split up to be parallel over fresh sessions from the start I do not think there is a place for subagent delegation at all. There should either be a super-agent that orchestrates and does no work, or a long running agent that can retrieve from previous sessions, not a worker that completes tasks partially and delegates the rest to other workers Don't design harnesses based on our assumptions of human behavior

1:09
Can Bölük avatar
⟳ PiG retweeted
Can Bölük@can1357·Nov 6

two big changes in 18.17.0, both backported from the upcoming omp²: our new streaming bash engine & integration with ovnfs, an agentic filesystem providing an alternative to git worktrees with much more desirable properties 🧵

Post attachmentPost attachment