Skip to content

Framework

Reflexion

Framework in which language agents keep written reflections from previous attempts and use them on later tries.

Known aliases

  • Reflexion

Current stories

buildOne report1 publisher

Instinct's unrequested shopping picks test how a possibly commission-earning agent decides to speak first

Three Instinct users told Business Insider its personal agent sent them shopping picks they never requested, including a $250.75 suitcase. None were shown to be paid, but with merchant commissions in Instinct's plan, when the agent pitches unprompted should be the user's call.

Publishers:runtimewire.com

Reality

Evidence45
Adoption
Not scored
Hype gap+15
Incentives70
Confidence50
investOne report1 publisher

Instinct is valued at ten times the yearly purchases its invite-only agent books

Instinct raised $1 billion at a $10 billion valuation this week, four times its August price, for an AI assistant open only by invitation. The price rests on its founder's claim of nearly $1 billion in yearly purchases routed through a free app.

Publishers:fortune.com

Reality

Evidence35
Adoption25
Hype gap+50
Incentives60
Confidence40
buildConfirmed3 publishers

Instinct raises $1 billion at a $10 billion valuation for an agent that operates users' phones and computers

Instinct raised $1 billion at a $10 billion valuation, four times the price TechCrunch reported for its August round. Its agent works through users' own screens and accounts, so permission and recovery are Instinct's to engineer before any app maker is asked.

Perspective Coverage

3 publishers
Builder
Builder 23%
Operator
Operator 27%
Investor
Investor 50%

Reality

Evidence55
Adoption20
Hype gap+45
Incentives60
Confidence60
leadershipOne report1 publisher

Instinct raised $250m at a $2.5bn valuation after handing VCs the first invites

Noah Shinn gave venture capitalists the first invites to his AI assistant. Instinct now carries a $2.5bn valuation. The technique for making agents learn from their own failures is one Shinn published in 2023, before GPT-4.

Reality

Evidence46
Adoption22
Hype gap+34
Incentives72
Confidence54
buildOne report1 publisher

Instinct's reported memory relies on keyword matching, not semantic search, with a once-a-day write job

Dhravya Shah spent three days probing the personal agent from the outside and reports git-tracked Markdown searched by keyword, with a background pass he clocked taking 23 hours and 16 minutes to commit one preference.

Publishers:runtimewire.com

Reality

Evidence42
Adoption24
Hype gap+28
Incentives76
Confidence58