Dartnixtrix

[Dartnixtrix @dartnixtrix360]

@Letta_AI @PrimeIntellect @NousResearch @Teknium @claudeai @OpenAI Yeah Letta is way better than competition

[Letta @Letta_AI]

FrontierMemory also allows measuring the ability of agent harnesses to improve over time. We find that Letta Dream and @PrimeIntellect's Prime Agent improve the most from learning from prior experience data.

[Dartnixtrix @dartnixtrix360]

@StatsWire Is this the $100 or $200?

[Letta @Letta_AI]

Introducing FrontierMemory: a new way to evaluate agent memory through downstream task performance.

While existing memory benchmarks focus on recall (saturated via agentic search), FrontierMemory focuses on how agents learn from experience.

[Charles Packer @charlespacker]

Modern "memory" benchmarks are saturated since they measure recall of facts -- in the coding harness / bash loop era, recall is solved, while continual learning in token space remains unsolved.

FrontierMemory is a new benchmark designed to actually measure self-improvement through memory.

It's built on a simple premise - if AI-generated memory is *good*, it should actually improve downstream task performance. An agent with good memory should be more efficient (lower cost), or it should be more capable (higher score) than memory-less agents.

When you measure memory this way, it turns out there's a very wide spread in frontier model capabilities. Opus 5.5 and GLM-5.3 for example are *significantly* better at generated useful memories than GPT-6.1 Sol.

FrontierMemory can measure overall harnesses as well: and it also turns out that different implementations of AI dreaming vary wildly in performance. For example, it may surprise you that @PrimeIntellect Agent's memory system works significantly better than Hermes Agent's.

FrontierMemory is a continuous benchmark - we will be adding more tasks and revising them over time, and will be adding extremely long-horizon RSI-style tasks in our next release.

If you're building an AI system with memory, please reach out / DM! Likewise if you're building models or harnesses and would like to submit.

[Dartnixtrix @dartnixtrix360]

@trq212 @carsonfarmer You joining OpenAI in cutting our usage too? Seems like the question is more towards “slow down, your usage is about to go away!”

Just kidding I know you will

[Dartnixtrix @dartnixtrix360]

@deepfates Letta

[Dartnixtrix @dartnixtrix360]

@OfficialLoganK is gemini argon gonna show up in antigravity IDE or whole IDE is on verge of deprecation?

[Dartnixtrix @dartnixtrix360]

@iruletheworldmo If this is real, really feels hearty and snug. Company having all my data literally.

[Dartnixtrix @dartnixtrix360]

@TJeparskis Don’t use it or upgrade to ultra

[Dartnixtrix @dartnixtrix360]

@iruletheworldmo @ForwardEditor You mean you, Theo and Amodei agreed?

[Dartnixtrix @dartnixtrix360]

@fofrAI It's good, we require a more stonger line also. Happy so far though

[wren @gnostic_snakes]

gemini 4 argon is 100% aligned

[Dartnixtrix @dartnixtrix360]

@thegitai @elshayib_ But that’s ok, shear amount of free plans they gave away on the pro tier ruins experience for ultra users, and no one gives such a vast ecosystem and goodies in $20.

[Dartnixtrix @dartnixtrix360]

@elonmusk @Kevin_Logan @bot Think about also getting mac vms

[Dartnixtrix @dartnixtrix360]

@elshayib_ Are you using gemini ultra for business? It may not see the model, though my work account shows now.

[Dartnixtrix @dartnixtrix360]

@elshayib_ Yes

[Dartnixtrix @dartnixtrix360]

@FASSTRspace @OfficialLoganK @_mohansolo doesn't show up currently. Might be a delayed rollout across surfaces

[Dartnixtrix @dartnixtrix360]

@OfficialLoganK @_mohansolo Hope to use it and make it my daily driver. Very happy after a long long time, hope gemini outcompetes soon.