Amir Elaguizy

Builder, Dad - YC S13 - Cofounder @PlayPokerSkill, @Cratejoy, MarketZero - Question the answers

[Amir Elaguizy @amirpc]

@scaling01 Tell it not to use create image tool

[Amir Elaguizy @amirpc]

AI sales emails are a reminder that just because superhuman intelligence is available doesn't mean it will be effectively wielded

[Amir Elaguizy @amirpc]

Hear me out: openclaw for keeping all your other agents logged in to shit

[Amir Elaguizy @amirpc]

Lmk when deep swe benches of opus 4.8 drop I sort of just don't believe anything else deep swe is the only bench that matches my experience

[Amir Elaguizy @amirpc]

Claude is just part of the onboarding for codex

[Amir Elaguizy @amirpc]

A humble proposal for the AI labs: before you use automated systems to ban paying users maybe use those same automated systems to say "hey you're doing this thing. We can tell. Stop it." Then ban them if it happens again.

[Rohan Paul @rohanpaul_ai]

Super important paper from Univ of Texas.

AI agents can slowly become less reliable after deployment, even when the model itself does not change.

The problem is that agents are often judged when they are fresh, but real agents keep changing because they summarize old chats, store more memories, update facts, and go through maintenance.

An agent that remembers you across weeks is really a small operating system wrapped around a language model: it writes notes, compresses them, retrieves them, updates them, and occasionally cleans house.

Every one of those steps can quietly rot.

A medication dose can become “a daily medication,” two similar clients can blur into one, a canceled subscription can remain active, and a schedule can vanish after a maintenance pass.

The uncomfortable finding is that the agent may still sound competent while becoming less exact.

The proposed AgingBench, a benchmark that checks whether an agent stays reliable across many sessions instead of only checking one clean starting point.

It studies 4 ways agents age: summaries can drop key details, similar memories can get mixed up, updated facts can stay stale, and maintenance can suddenly break memory.

The deeper lesson is that “give it more memory” is often the wrong repair.

If the fact was never written, retrieval cannot save it.

If the fact was written but crowded out, better summarization will not fix it.

If the fact is present but unused, the problem is not storage but the agent’s decision to trust or ignore what it retrieved.

This paper reframes deployed agents less like static models and more like aging infrastructure.

----

Link – arxiv. org/abs/2605.26302

Title: "Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems"

[Serena Ge (Datacurve) @serenaa_ge]

Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks.

On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.

[Simon Last @simonlast]

1/ Some things I've learned recently running coding agents on large-scale projects. Most of this contradicts advice from 6 months ago!

[Amir Elaguizy @amirpc]

Codex: Yes its fully implemented and tested and ready for review.

Small note: The docker container is out of disk space so nothing was tested.

[Amir Elaguizy @amirpc]

The most important thing the Gemini models do is create pressure on everyone else, keep it from being a pure two horse race, and make it clear Google isn't going to have their lunch eaten easily. Otherwise they are kinda meh

[Naval @naval]

The latest IQ test involves data centers and water.

[Amir Elaguizy @amirpc]

History will look back on "detecting AI generated content" as hilarious. It will be like detecting books typed vs written by hand on paper.

[Amir Elaguizy @amirpc]

Spent all day working with 140 IQ models that can't tell left from right and let me tell you...AGI is not here.

[Amir Elaguizy @amirpc]

@thsottiaux @reach_vb Thank you for treating your users with respect

[Tibo @thsottiaux]

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours.

We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening.

Apologies and now is the time for /fast maxxing.

[Amir Elaguizy @amirpc]

Well its officially easier to migrate off of some SaaS than deal with their support.

[Amir Elaguizy @amirpc]

@nwenzel 🔥

[Amir Elaguizy @amirpc]

These posts that 60% of code is written by AI at X company blow my mind. Who tf is still opening up VIM and doing this shit one key press at a time? If it's less than 99% you have a performance problem.

[Amir Elaguizy @amirpc]

I had gpt 5.5 xhigh organize all of the released UFO files, review all videos and images, categorize them into buckets of completely explained to not explained, etc.

Then asked it for a skeptical but curious analysis. Pretty interesting.