it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ultra. oh agents? you do that in spark actually. no, not gemini api managed agents, that’s different. for coding use jules. unless you mean the agentic ide, that’s antigravity. no, that’s the old antigravity, download the new one. actually gemini cli is being deprecated, use antigravity cli. no the flash model is smarter than the pro model. unless you need pro. if it’s video, use flow. no, flow uses veo. no, nano banana is images. actually that’s in gemini now. unless you’re in search, then it’s ai mode. no, research is notebooklm. anyway it’s all very simple.
long weekend checklist:
→ full rename, rebrand, new website
→ ready a launch for a completely new service/offering
→ secure a domain for a personal site
The @raycast team have done a great job with built‑in dictation. The only thing I'm missing from Wispr Flow is the automatic detection and addition to the custom dictionary.
@peduarte@raycast When text is added to a text field after dictation if I correct the spelling right after it will note that and add it to the custom dictionary itself (Vocabulary in Raycast parlance).
Basically it self improves in a completely frictionless way - honestly it’s very well done.
@peduarte@raycast When text is added to a text field after dictation if I correct the spelling right after it will note that and add it to the custom dictionary itself (Vocabulary in Raycast parlance).
Basically it self improves in a completely frictionless way - honestly it’s very well done.
@jessethanley@Travis_Jamison Yeah, you're not missing out on much. Opus responds well to GPT driving it for me, but that's very narrowly scoped to just problematic front‑end design stuff and copywriting.
Built some custom components for blog/article posts for my new site (live next week).
Really happy how they're coming together - here's one for sample emails.
1. If anyone can pull this off it’s the @FactoryAI team.
2. Genuinely believe this could only be released in a post Composer 2.5 world (not saying you need this model - saying it’s a line in the sand where we’re seeing the level competence we all saw emerge last Nov/Dec but at significantly lower pricing).
3. Everyone is attached to this being solely about absolute cost saving but it’s actually about being able to operate at all points along the Pareto frontier. The Factory team are smarter than to get into a pure lowest provider knife fight.
I trust them when they say they’re trying to build the software factory of the future and this yet another development to stack on top of things like Missions, Deferred Context Engine, and even (conceptually) subagents with Droids - all well before others show up with these things.
Introducing model routing to Factory.
Factory Router picks the right model for every task, automatically.
Maintain frontier performance while cutting costs by 25%.
Firstly I wasn't saying it was technically impossible before now. I was saying that it was only practically possible now. If it had actually been useful earlier, this would have already spread.
The difference is you need to meet a certain threshold for competence at the model level and we've only recently crossed that line.
It's also not necessarily just about going down to a less capable model. Sometimes task completion cost is lower on a higher per-token cost model because it gets the job done with fewer tokens and less iterations.
I wish Slack was:
- Agent-first
- Beautiful to use
- Integrated with agents natively so your Hermes or OpenClaw lives inside it
- Huddles worked seamlessly and were fun
- Built for teams of 1-3, not just teams of 300
- Truly a second brain similar to Obsidian
- Searchable without wanting to throw your laptop
- Designed around async, not constant interruption
- Voice first for mobile
- A place where I could see who's working on what right now without asking anyone
- Smart enough to know the difference between "I need you right now" and "whenever you get to this"
- A workspace where my agent could tap someone else's agent on the shoulder and coordinate without involving either human
- Designed so the new hire on day 1 has the same context as the person who's been there 3 years
-Something that felt like walking into a room of people building, not walking into a room of people typing
- A place where decisions are first-class objects
- Able to auto generate SOPs, skills, agents etc from conversation history
- Something that rewards deep work instead of punishing it with 47 unread notifications
Introducing the Lifetimely Profit Agent - powered by the $100Bn in GMV.
It uses the benchmarks from across all the GMV in Lifetimely, to find the highest leverage Profit opportunities in your business, and can actually take action to drive Profit.
It's live in Lifetimely right now!