PWV Portfolio Feed

DeepSeek V4.1 Flash now has $100 usage, next 3 days.

$10 GOAT → $100 credits.

After that, we're increasing it to $80. LFG!

🐐

Muse Wonder by Meta is now live in Command Code.

Most capable across agentic and coding tasks
Opus 5.5 and GPT 6 Astra class benchmark results

Available in Max plans and API.

3 more days 👀

Smaller isn't always faster.

What gets TOASTed in Postgres and when to keep pglz:

We've published multiple advisories affecting the dev server.

The main one is an arbitrary command execution when using some editors or through `launch-editor` on Windows.

Update now to the patched versions:
- Vite 8.3.3, 8.2.4, 8.1.6, 7.3.7, 6.4.4
- Vite+ 1.1.0

Links to each report below.

Command Code GOAT has three GPT models in its lineup.

· GPT 6 Luna
· GPT 5.6 Sol
· GPT 5.6 Luna

thank you Jim! and yes! it’s a whole different ballgame to the right of the dot

Last week in Command Code, a quick recap.

· Agr, our open decision model
· Cloud sessions with sandbox
· ACP support in editors like Zed
· Claude Haiku 5.5 (2x usage in GOAT)
· Mistral Large 4 (4x usage in GOAT)
· Glyph Cluster (free stealth model)
· Command Code Hooks demo
· 1st SF Tech Week event

Command Code now has two Claude models in the GOAT plan lineup.

· Haiku 5.5
· Sonnet 5.5

AWS's own docs say gp3 volumes can drop below 90% of provisioned IOPS 1% of the time.

That's 86 hours a year, per volume. Spread a database across 768 of them and there's a 99.65% chance one is hurting production right now.

closed models get better when one lab decides to ship.

open models get better every time anyone touches them. a quant here, a fine-tune there, a new inference trick from someone's weekend project.

one roadmap vs a million. i know which one i'm betting on.