UI Lead 💧 @leadui - Twitter Kullanıcısı

2 gün önce

We didn’t win this one @muhaj_dev but we definitely did our best and we will do even better on the next. Thank you for the experience @Badtheorylabs Until we meet again. #studiome

Bad theory labs

@Badtheorylabs

2 gün önce

The BTL Runtime Hackathon is decided. 42 projects. 72 hours. 40M tokens burned. We did not judge on vibes. Every repo was code-audited. Every live app was tested. Every runtime call was verified against the usage ledger. Not vibes. Receipts. Here are your winners. 1st place: DOCENT ($500) A six-engineer AI swarm that reads your repo, argues about what it finds, and remembers what changed the next time you ask. 900+ verified runtime calls across chat, embeddings, and streaming, all load-bearing. Code: https://t.co/0UQEd1xXON Try it: https://t.co/TeJkjmY9DQ Demo: https://t.co/pLxu5NCltV 2nd place: TRIBUNAL ($300) Six model roles (panelists, judge, claim extractor, verifier, skeptic) debate live through the Runtime, with failover when a route dies and every cost header on-screen. The highest verified score of the event. Code: https://t.co/fnZ4f7E1eX Try it: https://t.co/DcZO8sxw2I Demo: https://t.co/r2UDaA6wHq 3rd place: CRITCACHE ($200) Code review built on cache economics. Cold run vs warm run, with the receipts to prove the savings. The cleanest build we audited: every commit inside the window, zero red flags. Code: https://t.co/mE6837pSC2 Site: https://t.co/4IFVy7PGO9 Demo: https://t.co/r0LFYE6ax7 Best Use of Runtime: VERIFI ($100) An autonomous QA agent that browses your app and finds real bugs. Per-stage cost ledgers built from our headers, cache-aware retries, and a real browser vision loop. 6M+ tokens of verified workload. The Runtime was not decoration, it was the engine. Code: https://t.co/DtGRZDKxAH Demo: https://t.co/rFaCiNtehL Honorable mentions, all code-audited, all real: readIQ, student RAG with vision OCR: https://t.co/47n6D3E0Kv Vintage, verified-computation investing agent: https://t.co/EpudCkDCh7 Dispatch, cache headers as product data: https://t.co/oJEuLcqa8c Crosscheck, extraction you can trust: https://t.co/XGIMQlnqpV flex, multi-model contract audit swarm: https://t.co/ssTvxeHub4 HIVE, scoped memory with auditor veto: https://t.co/mCqiLf6NN5 Icaruz, cache-economics knowledge market: https://t.co/eCJ5f5YUQY BtlRadar, cost-tiered security cascade: https://t.co/MA9SAF2cDT Helena Labs, incident copilot: https://t.co/94pEBXqXZz How we judged: 30 points Runtime use, 25 usefulness, 20 execution, 15 creativity, 10 presentation. Then we verified everything. Cloned every repo. Probed every live app. Matched every claim against the ledger. Congratulations to every team that shipped. The next event is coming.

Badtheorylabs's tweet photo. The BTL Runtime Hackathon is decided.

42 projects. 72 hours. 40M tokens burned.

We did not judge on vibes. Every repo was code-audited. Every live app was tested. Every runtime call was verified against the usage ledger. Not vibes. Receipts.

Here are your winners.

1st place: DOCENT ($500)
A six-engineer AI swarm that reads your repo, argues about what it finds, and remembers what changed the next time you ask. 900+ verified runtime calls across chat, embeddings, and streaming, all load-bearing.
Code: https://t.co/0UQEd1xXON
Try it: https://t.co/TeJkjmY9DQ
Demo: https://t.co/pLxu5NCltV

2nd place: TRIBUNAL ($300)
Six model roles (panelists, judge, claim extractor, verifier, skeptic) debate live through the Runtime, with failover when a route dies and every cost header on-screen. The highest verified score of the event.
Code: https://t.co/fnZ4f7E1eX
Try it: https://t.co/DcZO8sxw2I
Demo: https://t.co/r2UDaA6wHq

3rd place: CRITCACHE ($200)
Code review built on cache economics. Cold run vs warm run, with the receipts to prove the savings. The cleanest build we audited: every commit inside the window, zero red flags.
Code: https://t.co/mE6837pSC2
Site: https://t.co/4IFVy7PGO9
Demo: https://t.co/r0LFYE6ax7

Best Use of Runtime: VERIFI ($100)
An autonomous QA agent that browses your app and finds real bugs. Per-stage cost ledgers built from our headers, cache-aware retries, and a real browser vision loop. 6M+ tokens of verified workload. The Runtime was not decoration, it was the engine.
Code: https://t.co/DtGRZDKxAH
Demo: https://t.co/rFaCiNtehL

Honorable mentions, all code-audited, all real:
readIQ, student RAG with vision OCR: https://t.co/47n6D3E0Kv
Vintage, verified-computation investing agent: https://t.co/EpudCkDCh7
Dispatch, cache headers as product data: https://t.co/oJEuLcqa8c
Crosscheck, extraction you can trust: https://t.co/XGIMQlnqpV
flex, multi-model contract audit swarm: https://t.co/ssTvxeHub4
HIVE, scoped memory with auditor veto: https://t.co/mCqiLf6NN5
Icaruz, cache-economics knowledge market: https://t.co/eCJ5f5YUQY
BtlRadar, cost-tiered security cascade: https://t.co/MA9SAF2cDT
Helena Labs, incident copilot: https://t.co/94pEBXqXZz

How we judged: 30 points Runtime use, 25 usefulness, 20 execution, 15 creativity, 10 presentation. Then we verified everything. Cloned every repo. Probed every live app. Matched every claim against the ledger.

Congratulations to every team that shipped. The next event is coming.

9

35

5

7

3K

1

5

1

0

100

UI Lead 💧

@leadui

Sotwe'de En Son Ziyaret Edilenler

Senin İçin Trendler

En Popüler Kullanıcılar