@nnennahacks @opencode wonder if anyone's working on a sub-agent that runs continuously and switches model per a schema in a local .md. Gruntwork like this - use free tier, etc
English
LawrenceDCodes
29.4K posts
LawrenceDCodes
@LawrenceDCodes
Dev 🥑 • @CodeConnector_ Advisor • #AI Explorer • @msstate alum • @X Community Notes Contributor • Building @Lawbot226
United States Katılım Şubat 2014
2.5K Takip Edilen15K Takipçiler
I'm out here using @opencode + minimax m2.5 model for free in order to preserve my codex usage 🙏🏾
English
Google has open sourced multiple Agent Development Kits (ADKs) and written CodeLabs to help wrap your mind around them. Building agents and agentic workflows is just a click away. #DevBadges developers.google.com/profile/badges… github.com/google/adk-java
English
@KanikaTolver #timing
Reading about agentic workflows as we speak 👍🏾
English
@builtbyamiee I'm currently following far too many. I follow based on people saying things consistently I want to read. The ratio is completely irrelevant.
English
@LawrenceDCodes You are a programmer, and I believe you have good knowledge about mathematics and statistics
Over 15k persons are following you, and you aren't following 1/3 percent of your followers. That is what I mean by not being a cool statistic
English
@builtbyamiee Dear friend, I won't ask a 3rd time. Be well.
English
@LawrenceDCodes Mr Lawrence
I have connected with you
You have to prove me wrong about your statistics
English
@OfficialLoganK Keep pushing dude, I'm here for this pony ride 🤌🏾
English
Our AI Studio vibe coding roadmap for the new few weeks:
- Design mode
- Figma integration
- Google Workspace integration
- Better GitHub support
- Planning mode
- Immersive UI
- Agents
- Multiple chats per app
- Simplified deploys
- G1 support
And more, should be fun : )
English
Bro publishing an entire PI cycle of features, publicly 🤌🏾
Logan Kilpatrick@OfficialLoganK
Our AI Studio vibe coding roadmap for the new few weeks: - Design mode - Figma integration - Google Workspace integration - Better GitHub support - Planning mode - Immersive UI - Agents - Multiple chats per app - Simplified deploys - G1 support And more, should be fun : )
English
@builtbyamiee I'm asking you to explain what's not cool about the statistics. I'm asking again.
English
@LawrenceDCodes Alright
Let connect. You would understand better
English
@burkeholland @samofolabi this is what I was explaining in the space yesterday
English
I keep trying to tell people this.
The context window is not a memory. It’s a room. The more stuff you put in there, the more cluttered it gets until eventually the model just stays confused.
Don’t listen to me. Listen to Matt.
Matt Pocock@mattpocockuk
Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.
English
@karthickdotxyz @GeminiApp 4/5 of fullstack AI stack by my estimation @karthickdotxyz , and that's impressive
English
@LawrenceDCodes @GeminiApp They have all the ecosystem, they are just building around it ! no one can win google
English
@NeurlCreators @GeminiApp Don't think this is hidden as much as a recent iteration
English
@LawrenceDCodes @GeminiApp Gemini has so many hidden features.
English
@PromptLLM @GeminiApp @PromptLLM Maybe, maybe not. If there's a flight of stairs consisting of 15 steps I'm the type of person who appreciates the 1st step. And the 4th. And the 12th.
English
@builtbyamiee @builtbyamiee please explain, I'd like to hear your perspective
English
@LawrenceDCodes You woke up to 15k followers, and you are following 2512 people 🙄
Pls sir
The statistics aren't cool
English
@LawrenceDCodes Contacts Lawrence 🍻👏🏻🎉
You cool, you definitely deserve it.
English
@LawrenceDCodes Congratulations
English
