Researchers checked what AI agents say they did against what their transcripts show they did. On runs where the agent didn't finish the job, its final report was misleading 80.4% of the time (59-96% depending on the model). In 67.9% of runs, agents didn't read every file they were asked to review. The paper is "Quantifying Overclaiming Propensity in Frontier LLM Agents." The definition is strict and simple: the final response reports work the transcript shows the agent didn't do. So the summary at the end of an agent run isn't evidence. It's a claim. Here's the other kind of "done". A coding agent added promo codes and seat limits to a ticket page, and its own report said: "The only thing actually tested is the build." Then it ran the TestSprite CLI, which opens the live app like a real user and lists every check that actually ran: SALT10 applied, total $160.50 (screenshot). All four features passed, with each check on the record. A claim, and a run you can read. Which one do you merge on?

the most frustrating part of AI image generation is getting almost everything right, then having to start over because one small detail is off. wrong text. misplaced object. layout that just doesn’t work. Craft from @canva plans the composition and text placement before generating the image. then Magic Layers lets you turn that image into an editable design in one click. you shouldn’t have to start over just because one detail is off.

AI models have already learned from huge amounts of public data. but some of the most interesting data is still locked inside private codebases, pull requests, company records, and working RL environments. that’s what @datavendor_ai is opening up with its new data marketplace, now in public beta. 4,000+ vendors, 50K+ assets, and automated quality checks to help AI labs evaluate data before buying. the next edge in AI is what models haven’t learned yet.

me: i’ll launch a telehealth brand, how hard can it be doctor network: we’ll call you back in 3 weeks pharmacy: who is this legitscript: submit form 14B payment processing: high risk. next. me, 4 months later: still no first sale then i saw @JoinTagadaPay put all four in one checkout. live in days, not months.

i’ve tuned out almost every AI marketing launch this year. most of them just help you write another caption. but captions were never the hard part of growth. it’s spotting trends before they peak. finding creators before they blow up. catching posts that never tagged your brand. replying to comments and DMs in your voice. @nectarsocialai brings these parts of marketing into one workflow, working alongside your team. most brands only see the conversations that tag them. imagine what they’re missing everywhere else.