Dillon Hong

product @ airops

[Dillon Hong @dillonhong]

@annalisekrueg Pass^k son or pass@k daughter?

[Dillon Hong @dillonhong]

@jessperate /goal please complete list

[New York Metro Weather @nymetrowx]

OKX issues Tornado Warning [tornado: RADAR INDICATED, hail: <.75 IN] for Nassau [NY] till 7:15 PM EDT https://t.co/wYIO1thrkL

[Dillon Hong @dillonhong]

@turbopuffer Huge @lateinteraction

[Dillon Hong @dillonhong]

@realmcore_ @helixdb @neo4j When in doubt the answer is always Postgres

[Dillon Hong @dillonhong]

@jessperate @WisprFlow 7.5/10

[Dillon Hong @dillonhong]

@can @modal I like modal. Me modal

[Dillon Hong @dillonhong]

@RhysSullivan @ExaAILabs @turbopuffer got a nice one too

[Dillon Hong @dillonhong]

@yescynfria How do I invest

[Dillon Hong @dillonhong]

@charliermarsh Like asking if the sun is gonna rise at this point

[Dillon Hong @dillonhong]

@melodyskim @tylerangert @left_pad This is sick! Will have to give it a try

[Dillon Hong @dillonhong]

@Sirupsen Congrats team!!

[Alex Halliday @alexhalliday]

Welcome to the AI Search MCP race. The category is full of "coming soon" roadmaps for operating from chat.

We shipped that in February.

The @AirOpsHQ connector has been live in Claude for 3 months. Customers like Carta, Webflow, and Chime have been pulling citation data, running competitive analysis, and launching refresh and creation strategies from chat since then. Not a phase 2. Not a Q2 plan. Live, in production, in their daily ops.

In fact, our team was on stage at @AnthropicAI Code with Claude event in London today, walking through how we built on top of this foundation. Huge moment.

For those new to the race, catch up when you can. If you need a refresher, here you go: https://t.co/UKpbeEwIZG

[Dillon Hong @dillonhong]

@p0 team is world class. next to none 🤫

@lukaslevert @TinaJiang20 @agarwalipshita

[AirOps @AirOpsHQ]

If you’ve created content with AI, you’ve run into hallucinations, broken links, and shallow research.

That’s why we’ve partnered with @p0: to ensure your content’s sources are recent, high-quality, and fact-checked. All essential to win AI search.

[Dillon Hong @dillonhong]

@yerbamatt @cynthiamcgillis @theHankTaylor @mgonto @hyperagentapp What about running and chaining skills at scale? Lemme know if you want a run through 🙂

[Dillon Hong @dillonhong]

@yerbamatt @cynthiamcgillis @theHankTaylor @mgonto @hyperagentapp Do you like the table?

[Dillon Hong @dillonhong]

@chloepark Chase friction. Chase niche 🙂

[Dillon Hong @dillonhong]

@Simeon_Cps Currently visiting London for the first time and definitely see the appeal. Ton of character. Transit is super straight forward too

[Dillon Hong @dillonhong]

@DimitrisPapail Couldn’t be implied that the model attends to the action output because the tool call is dependent on previous action?

Then masking allows you to optimize for general problem solving without explicitly exposing the world model. That frees up weights to learn other things no?