archis.eth 🦇🔊

curr @Covalent_HQ | ex @encifherio @0xStackr @pushchain | @0xpolygon Fellow’22 | @Arsenal ♦️

[archis.eth 🦇🔊 @Arch_0125]

Update on BlobMerger project built during @ETHGlobal Scaling Ethereum'24 - won best appchain built on @AvailProject

changelogs
> add gas auction for submitting micro blobs
> use 0/1 knapsack to form batches
> more accurate blob base fee estimation acc. to EIP4844 specs
> zk proofs for micro-blob inclusion in the main blob
> zk proof verifiable by smart contracts
> blob data extraction and conversion from hex

Old repo:https://t.co/RyELjegapo
New repo:https://t.co/aRoNG9HV6U

[archis.eth 🦇🔊 @Arch_0125]

I’ve been diving deep into memory engines for LLMs — specifically how far we can reduce token usage while improving long-context accuracy.

So I built a memory layer for LLMs and ran it against the full LongMemEval-S benchmark:

Thanks to @supermemory and @mastra for their benchmarking framework which i used a reference to set up mine

500 questions
gpt-4o actor + gpt-4o judge
Best-of-3 judging passes

Results:

82.22% unweighted accuracy
80.80% micro accuracy

Per-category breakdown:

• SSU: 92.86%
• SSA: 94.64%
• SSP: 70.00%
• KU: 88.46%
• TR: 76.69%
• MS: 70.68%

The system was strongest on single-session factual recall, and weakest on multi-session aggregation + temporal reasoning

[archis.eth 🦇🔊 @Arch_0125]

The architecture ended up being a mix of retrieval, reranking, and fallback reasoning:

Retrieval side:

• Hybrid dense + BM25 fusion
• Heuristic + cached LLM query expansion
• MMR diversity
• Recency bias for knowledge-update questions
• Time-anchor bias for temporal questions
• Optional cross-encoder + LLM listwise rerank

Answer side:

• Chunk-level hits rolled up into session-level evidence
• Retrieval-confidence scoring
• Low-confidence fallback that injects raw transcript from top sessions
• Pluggable single-shot or self-critique synthesizer

[archis.eth 🦇🔊 @Arch_0125]

I’ve been diving deep into memory engines for LLMs — specifically how far we can reduce token usage while improving long-context accuracy.

So I built a memory layer for LLMs and ran it against the full LongMemEval-S benchmark:

Thanks to @supermemory and @mastra for their benchmarking framework which i used a reference to set up mine

500 questions
gpt-4o actor + gpt-4o judge
Best-of-3 judging passes

Results:

82.22% unweighted accuracy
80.80% micro accuracy

Per-category breakdown:

• SSU: 92.86%
• SSA: 94.64%
• SSP: 70.00%
• KU: 88.46%
• TR: 76.69%
• MS: 70.68%

The system was strongest on single-session factual recall, and weakest on multi-session aggregation + temporal reasoning

[archis.eth 🦇🔊 @Arch_0125]

The more interesting part was token efficiency.

Compared to the full-history Chain-of-Note baseline, on the same 500-question dataset and prompt template:

• ~3,200 input tokens/question vs ~14,600
• 78% fewer input tokens
• +22pp higher accuracy

[GoldRush - powered by Covalent @goldrushdev]

Hyperliquid Markets Weekly Heatmap

DeFi: +11.4% ✅
Stocks: +11.2% ✅
Layer 1: +4.0% ✅
HIP-3: +3.8% ✅
Indices: +3.3% ✅

Meanwhile, AI: -17.5%. RWA: -5.3%. Commodities: -4.5%.

DeFi and Stocks running together while AI gets wiped

The market isn't rotating out of crypto. It's rotating out of the narrative - How are you positioning yourself?

Source: https://t.co/NH6eMenifJ

[Covalent @Covalent_HQ]

https://t.co/ltQeUjkpvB

[archis.eth 🦇🔊 @Arch_0125]

@0xdhruva @conduitxyz congrats ser!

[Trench @TrenchExchange]

PRIVATE BETA LIVE

Catch what others miss, before it’s too late

Trench is here. Lock in, dominate the market 🦾😼

[archis.eth 🦇🔊 @Arch_0125]

@Sampriti026 nashe kam kro bhai

[Y Combinator @ycombinator]

CompliantLLM (@FiddleCubeAI) detects data leaks into any third-party GenAI tools used across your company. It identifies GenAI-specific attacks to catch breaches in both approved and unapproved AI workflows.

https://t.co/AFgRpUoYKl

Congrats on the launch, @kaushik_himself & @nupoor_neha

[archis.eth 🦇🔊 @Arch_0125]

@daksh0x pop out the key with a guitar pick, and clean it, pretty easy to do i would say, just be gentle while putting it back, there’s some sliding mechanism

[Trench @TrenchExchange]

Trenchers, stand by!

A silent vessel cuts through the dark, armed with what comes next

[PRIVATE BETA] is loading…

[archis.eth 🦇🔊 @Arch_0125]

@nitanshu Should checkout @OfflineProtocol

[archis.eth 🦇🔊 @Arch_0125]

@daksh0x @gakonst Yo ser, would like to collab and get it to prod

[archis.eth 🦇🔊 @Arch_0125]

@prrthamm @thenetworkstate Crazyyy stuff ser

[Nitanshu (pqc/acc) @nitanshu]

I can literally buy TSLA stock using TRUMP memecoin XD

That too even privately

Using @encifherio Thanks to @JupiterExchange

[Nitanshu (pqc/acc) @nitanshu]

You can just buy US stocks privately

[archis.eth 🦇🔊 @Arch_0125]

@MurrLincoln @coinbase @CoinbaseDev Yeah ive roadmap for scaling the proj to the mainnet, as well as some ideas to improve the latency and throughput of the x402 protocol itself, lmk if i can drop you a DM

[archis.eth 🦇🔊 @Arch_0125]

Played around with @coinbase x402 protocol and here’s what I built recently

Codey ✨ - unlock true pay-as-you-go in your AI powered code editors. Use your wallet as API key, top-up USDC & pay-per-call. Pick your context, let smart agents pick the best model for price & accuracy. You control the budget, no flat subscriptions, no wastage.

Where to next
- Currently wallet is stored in VSCode SecretStorage, can be extended to use CDP wallet with session keys and permissions
- Democratising model choice, anyone can host their service and provide api endpoints and set their fees

Check out the demo, DM to get access and try out

cc @CoinbaseDev

[archis.eth 🦇🔊 @Arch_0125]

@BitGPTnetwork @coinbase @CoinbaseDev Before getting the response

[archis.eth 🦇🔊 @Arch_0125]

@BitGPTnetwork @coinbase @CoinbaseDev For sure, i would love to try it out, since im looking for faster transaction confirmation times, since imo paid API endpoints are generally supposed to give higher throughput, which kind of takes a toll if the user has to wait a significantly longer time for txn confs