First time jumping into vercel sanboxes ๐๐
Built an AI native content studio for thinking backward where I can collaborate with Agents of my choice! (starting with claude code via the SDK)
Works like a charm for spinning up long running agents!
1. Because of vercel OIDC you dont have to configure anything, it just works.
2. API super intuitive.
3. Harness of your choice!
Probably going to switch over to gateway next. The tools were seriously built to just work.
kudos for making vercel AI native. @vercel@rauchg
@danshipper@every Do you accept applications for people with no editing experience ? ๐คฃ
Just kidding I probably wouldnโt be good at it but love every!
Been working with execs on AI rollouts for the last 14 months.
This is the most common level-by-level progression I see:*
Level 1: Run company wide AI audit, which includes mapping key processes, interviewing SLT/ELT, and surveying rank-and-file employees.
Level 2: Finalize post-diagnostic read out, which lays out AI transformation timeline by initiative. Prioritized by ROI, risk profile, and cultural support.
Level 3: Company realizes their data ducks arenโt in a row, which leads them to working on the โCompany Brainโ panacea.
Level 4: In tandem, start by investing in coding agents for the engineering/product org.
Level 5: Get enterprise access to general purpose LLM for subset of non-technical AI champions.
Level 6: Expand enterprise access to all non-technical employees.
Level 7: Run small cohort of workshops for ELT and AI champions so they get the most out of the technology.
Level 8: Roll out training/enablement program company-wide.
Level 9: Company runs AI hackathon, which lets employees bubble up solutions to problems from the AI audit as well as new problems.
Level 10: Leadership reviews and prioritizes employee hacks and decides which initiatives to take from prototype to production.
Level 11: First AI build tackled is typically quick win to some back-office process with attributable hard ROI where cultural pushback is expected to be low.
Level 12: Token efficiency/cost optimization becomes major focus as AI budget begins to balloon in eng org.
Level 13: As internal momentum builds & longer ROI leash is given, cycle of problem identification โ> process map โ> prototype โ> test/harden/secure/measure โ> scale is followed leveraging initial AI readout, hackathon findings, etc.
Level 14: Company starts moving further along the spectrum from deterministic workflow to self-guided agent as the AI muscle expands.
*Note: these levels can appear in different order or happen simultaneously vs. sequentially depending on the companyโs context
Anthropic has pushed AI forward dramatically over the past two years. It's currently the crown jewel of US AI tech.
The Feds don't like @DarioAmodei because he won't do all their bidding. And so, we've now entering the Soviet-style propaganda portion of the program with the White House feeding every reporter it can find with laughable claims like Dario is unreachable at a wellness retreat. Come on.
I'd hoped the US would not be self-defeating on AI, since it's kinda one of the last hopes the US has versus China. But here we are . . . . already
@MatthewBerman Amazon has had a dramatic increase in cyber attacks on companies running on their infrastructure โ if this makes it easier to cyber attack Iโd bet that has something to do with it.
@sydneyrunkle@hwchase17@LangChain
Don't know who the best person to ask this is, but my team is interested in building a custom checkpointer and noticed the current implementation is in alpha, any indication on when it will leave alpha and become more stable?
New for Apple developers: Foundation Models support for Claude lets developers use Apple's Foundation Models framework to call Claude for multi-step reasoning, code generation, and longer context.
@burkov Honestly just when I want a little more out of a search, but the free Experience is getting worse and worse by the day.
Used to be a lot better free tier.
Computer looks good but donโt see a reason to use it over Hermes.