Wilford Lam retweetledi
Nearly $100B in USDT0 volume has already moved at the speed of the internet.
Powered by LayerZero.
USDT0@USDT0_to
English
Wilford Lam
930 posts
Wilford Lam
@wlam919
Scaling finance @layerzero_core | prev @doordash
Vancouver Katılım Şubat 2012
306 Takip Edilen122 Takipçiler
Wilford Lam retweetledi
Opus 4.8 is out, but even better:
- same price as opus 4.7 today
- /fast is 3x cheaper!!
- dynamic workflows for max agent orchestration
Claude@claudeai
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.
English
🔥
Matthew Lam@mattlam_
Built out a Starship V3 appreciation page using Grok Build to test out Grok's frontend and design taste, and congrats to the @SpaceX team!! Keep in mind Grok Build is still in beta, but here are my thoughts testing for this webapp: Pros: - Grok's design taste: didn't spend that much time getting the design cleaned up, but I think it's pretty decent compared to other agents. - access to X: X is one of best sources of latest news, and grok build has X tools built into it, which I think will be a huge advantage for any current event related agents, or agent needing the most up to date info. (all tweets, videos, images on the page were fetched by Grok through X). - ability to figure out appropriate tool use - tui exp and parity on /commands - context window seemed efficient Feedback: - long running tasks: I tried telling the agent to implement -> spin up review subagents -> fix -> review and repeat until no findings, but often the agent stopped even though it knew there were new findings and told me to just say "go" to continue. - /goal is missing but likely in the works, and I think it'll help dramatically with ^ - self verification: I built in a /self-test skill into all of my agent work, but Grok would say something is done though it wasn't done or verified. Do think other agents do this still, but Grok mischaracterizes "done" more right now - browser use and plugin, that's likely in the works - nit: some keybindings and normal tui exps I come to expect with agents is different, will have to test more to see if I like these changes. Link below ⬇️
ART
Built out a Starship V3 appreciation page using Grok Build to test out Grok's frontend and design taste, and congrats to the @SpaceX team!!
Keep in mind Grok Build is still in beta, but here are my thoughts testing for this webapp:
Pros:
- Grok's design taste: didn't spend that much time getting the design cleaned up, but I think it's pretty decent compared to other agents.
- access to X: X is one of best sources of latest news, and grok build has X tools built into it, which I think will be a huge advantage for any current event related agents, or agent needing the most up to date info. (all tweets, videos, images on the page were fetched by Grok through X).
- ability to figure out appropriate tool use
- tui exp and parity on /commands
- context window seemed efficient
Feedback:
- long running tasks: I tried telling the agent to implement -> spin up review subagents -> fix -> review and repeat until no findings, but often the agent stopped even though it knew there were new findings and told me to just say "go" to continue.
- /goal is missing but likely in the works, and I think it'll help dramatically with ^
- self verification: I built in a /self-test skill into all of my agent work, but Grok would say something is done though it wasn't done or verified. Do think other agents do this still, but Grok mischaracterizes "done" more right now
- browser use and plugin, that's likely in the works
- nit: some keybindings and normal tui exps I come to expect with agents is different, will have to test more to see if I like these changes.
Link below ⬇️
English
If oil closes above $100, what else moves?
Our Correlated Markets API!
Start from any prediction market, get related events by real-world outcome signal, expand (same thesis) or hedge (opposite).
Strait of Hormuz re-opening hedged against oil above $100 by December? We got you.
English
Our new prediction markets podcast, PRICED IN, kicks off tomorrow at 10a ET / 5p UTC.
@ZHeerwagen will be joined by @Lewsiphur to talk prediction markets regulation and $47M in action on aliens existing by 2029.
You don't want to miss this!
English
Qualifiers for the 2026 @rolandgarros French Open are in full swing.
Prediction markets are coming online as well. Here are the latest odds.
Who are you taking in the men's and women's brackets?
English
Wilford Lam retweetledi
We’re sharing our completed post-mortem on the April 18th incident, prepared with @Mandiant and @CrowdStrike. We are publishing both an executive summary and the full report at the link below.
Over the past four weeks, we’ve worked with hundreds of partners to help them understand their current security posture, and harden it where appropriate. We’ll continue this work, alongside taking additional proactive steps for the benefit of not only our partners, but also the ecosystem as a whole.
We want to extend our thanks to our partners for their support and patience this past month. There’s a reason that over $12 billion has moved across the network in the past four weeks, and why the world’s most valuable asset issuers have stood by our side: they believe in us, in what the LayerZero protocol has to offer, and in the value of modular, isolated, application-controlled security.
The work continues. And we look forward to continue showing up for the applications that trust us with their business, as well as the broader ecosystem.
layerzero.network/blog/layerzero…
English
Wilford Lam retweetledi
Introducing Gemini Spark ✨
It’s your 24/7 personal AI agent that helps you navigate your digital life, taking action on your behalf, and under your direction.
🧠 It runs on Gemini 3.5 and is built on @Antigravity, so it can perform long-running tasks easily in the background.
⏱️ And because it runs on dedicated virtual machines on Google Cloud, you don’t even need to keep your laptop open.
🧰 Spark will integrate seamlessly with Google tools, and soon with third parties through MCP.
#GoogleIO
GIF
English
Wilford Lam retweetledi
Google is killing the gemini CLI and consolidating it into @antigravity AntiGravity CLI!!
starting today, antigravity CLI will also be available to everyone. Links below ⬇️
English
Wilford Lam retweetledi
not enough people know about /side and it's underrated. Think claude's /btw but add:
- multiple message followups allowed
- you can spin up > 1 /side chats
ask questions while the agent is working on your main session, or ask questions to explore other directions, and it won't affect your session's context!
Peter Steinberger 🦞@steipete
@Dimillian /side !
English
Wilford Lam retweetledi
Built out a yolo /remote-control in the Codex cli using /goal.
- /remote-control starts a tiny server on laptop
- generates fresh token and qr code
- phone connects through webapp
- full sync between phone and laptop codex
- touch grass
A glimpse into what @OpenAI will cook up, we're just waiting on that Codex iOS now 👀
Also a demo of how powerful /goal is, especially prototyping, most of this was done overnight by Codex while I was sleeping lol
Matthew Lam@mattlam_
Codex just released remote control!! 👀 If you’ve ever wanted to continue your codex session while touching grass, OpenAI is making it happen, and with the Codex iOS incoming. - start a codex session on your local machine - remote control - continue on codex iOS
English
You know how before you'd have to be selective on your side project ideas?
Codex + /goal + 10x'ed rate limits solves that problem for me, crazy.
English
Wilford Lam retweetledi
Check out @SIGKITTEN’s Kitty app for the best mobile exp, and it’s free
Codex, Claude, wtv else agents built in for you to choose
SIGKITTEN@SIGKITTEN
5 stars, works great on iPad and android, has codex with linux, themes, backgrounds... and a wild update on the way you don't need to wait for the codex mobile app, kitty is totally free
English
Wilford Lam retweetledi
Codex just released remote control!! 👀
If you’ve ever wanted to continue your codex session while touching grass, OpenAI is making it happen, and with the Codex iOS incoming.
- start a codex session on your local machine
- remote control
- continue on codex iOS
Codex Releases@CodexReleases
Codex 0.130.0 is released. Highlights: - Added `codex remote-control` as a simpler entrypoint for starting a headless, remotely controllable app-server. - Plugin details now show bundled hooks; plugin sharing exposes link metadata and discoverability controls. - App-server clients can page large threads with unloaded, summary, or full turn item views. - Bedrock auth can now use AWS console-login credentials from aws login profiles. Complete details in thread ↓
English
Wilford Lam retweetledi
Codex 0.129.0 is moving to a bigger shift in /plugin work and session resume:
- plugins are moving towards shareable workflows for teams in workspaces
- think agent skills on steroids, but for teams
- team review checklists, playbooks, best practices, etc.
I've also said many times that /resume and /fork needs a major overhaul since it's so important to work continuation, and they're finally giving it to us:
- searchable by text
- preview conversation summary
- view full transcript
Demo for new /resume /fork and /hooks
Codex Releases@CodexReleases
Codex 0.129.0 is out. Highlights: - Vim modal editing added to the TUI composer, with /vim command, default-mode config, and Vim-specific keymap contexts - Redesigned session resume/fork picker; raw scrollback mode, /ide context injection, and workspace-aware /diff added to TUI workflows - Plugin management gains workspace sharing, access controls, source filtering, marketplace upgrade flow, and remote bundle sync - Hooks are browsable and toggleable from /hooks, with compaction lifecycle hooks and PreToolUse additionalContext support Complete details in thread ↓
English
OpenAI 5/5 event was attendee stacked, will say more after I get back some rest 😂
Lots of learnings, but for now here’s @sama from afar (I should’ve asked for a selfie), @romainhuet and @PaulSolt :)
English
Wilford Lam retweetledi
Codex 0.128.0 is huge, even better than a @thsottiaux reset.
Codex is moving more goal oriented with a new /goal command, think Ralph loop on steroids:
- /goal to set a new goal
- after agent turn finishes, Codex injects a message nudging the model to pick the next concrete action, if the user doesn't type anything
- goal requirements are mapped to evidence (files, test results, pr, etc.)
- model can only update goal to mark things complete
Also finally in version 128, "codex update" is supported 🎉
Codex Releases@CodexReleases
Codex 0.128.0 is released. Highlights: - Persisted /goal workflows with TUI controls to create, pause, resume, and clear - Permission profiles expanded with built-in defaults; --full-auto deprecated - Plugin workflows: marketplace install, remote bundle caching, remote uninstall Complete details in thread ↓
English
Wilford Lam retweetledi
OpenAI cooked with the new /goal, can't wait for them to add /goal to the Codex app, I will definitely be using it like crazy.
Here Codex created two games for me while I went out for lunch, and some tips:
- /goal : starting point to setting your goal, for these simple games I tested really short prompts like "/goal create a copy of doodle jump"
- there's a 4000 prompt limit, /goal will fail to start above that limit
- /goal resume: interrupt the agent whenever, and ask questions like any regular conversation, then /goal resume and the agent continues to build towards goal.
- computer use: I already have this built into my /self-test skill and AGENTS.md, but always make sure to include a computer use self test service so the agent to verify it's work e2e.
Give it a try, and let me see what you build with /goal!
Matthew Lam@mattlam_
Codex 0.128.0 is huge, even better than a @thsottiaux reset.
Codex is moving more goal oriented with a new /goal command, think Ralph loop on steroids:
- /goal
English
👏
Matthew Lam@mattlam_
Getting a retweet from @gdb is a good time to take a pause and say thanks to all of you! Really proud and appreciate of hitting 1k followers, and an OSS project with 300 ⭐️, crazy. This is my promise to continue to share my best practical tips as we learn and improve together.
ART