We’re moving from agentic review from @coderabbitai to @GoEntire. CodeRabbit has been great, but with agents working across our full stack, we need to understand how a change came together as well as review the code.
One task can span backend and frontend changes, several agent sessions and a release. We’ve been recording decisions, tests and progress in Linear, but one issue ended up with 89 comments. The context was there. Finding it and getting the next agent up to speed was becoming a job in itself.
That’s where Entire fits better for us. The conversations and checkpoints stay with the code. Brain and memories help agents pick up earlier decisions and lessons, and Graph helps them understand the code and what depends on it. We spend less time explaining the same things again.
With DB integration tests, browser checks and a separate release harness - evals in Trails alongside that context fits how we want to review the work, understand what passed and see what still needs checking.
That’s what’s driving the move as we bring more agents into development.
Running a compact engineering team going all-in on agentic dev, we love @GoEntire.
✅Checkpoints show how a change happened.
🤖Agentic Search finds past decisions.
🧠 Continuous Memory carries context forward.
🗺️ Trails puts evals into review.
More agents helping without us becoming the bottleneck.
Faster development, stronger checks, and visibility into the why behind the what.
The PR is in now firmly in our rear-view.
Rock on, team Entire.
Definitely up there as one of my favourite recent additions to Codex - even if it does feel like I'm giving away just that little bit more brain to the agent 😕
Now in beta: composer predictions in Codex for Pro users.
Codex can now suggest your next message based on your conversation and how you talk to it.
One of the most loved new features we've ever tested internally.
2
80
A sobering dose of reality. For the time being.
The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by what appears to be a well orchestrated PR campaign — has drummed up considerable fear. I worry that it represents a setback for our field.
I have written frequently that fears of AI are overhyped. AI’s capabilities can be uncannily human-like and unpredictable, and it’s rational to worry when people who are directly involved express concerns. But I see the problems as a sign of the engineering work that ahead, rather than insurmountable barriers or the sky falling. AI technology continues to advance — which is a good thing! — but technical advances, poorly understood by the public, give those who seek to generate hype repeated opportunities to do so.
First, I don’t see any step up in the risk of human extinction from AI compared to a few months ago. The theories about this remain the same fantastical, science fiction scenarios as a few months ago. The biggest change in AI risk is its cybersecurity capabilities — a topic which we should take seriously — but this, too, will not lead to the end of the world.
The most notable recent event leading to increased fear was when an OpenAI team deployed an agent swarm that hacked into Hugging Face. Much of the popular press contained significant hype. For example, some publications reported that a swarm of 1,200 agents carried out the attack. While this was technically accurate, as I write this, I have about 1,300 processes running on my laptop. Yes, the ability to get large swarms of agents to work in parallel on a task is a significant technical advance, And, in computing, many processes run at the same time. So this shouldn’t be seen as some magical capability.
Additionally, OpenAI’s buggy sandboxing and monitoring processes were key to enabling this incident. Fixing these bugs and putting in place improved monitoring would be appropriate fixes, not pausing AI. There are many well known ways to attack software systems. The main advantage of AI agents is that they are relentless. They will tirelessly try many tactics — and have the patience to chain vulnerabilities together — that previously would have taken an infeasible amount of human effort. But in the long term, I believe the advantage will lie with defenders (because they have more information with which to identify bugs, which they can fix), but the cyber-threat landscape has changed significantly. There are still bottlenecks to identifying and exploiting a vulnerability. AI agents still have to try a lot of things to see what works, and taking these actions takes time and might be detected by defenders. This is why, even though it is now easy to obtain versions of leading open weight models that have had their guardrails removed or weakened, so they will not refuse to try to execute cyber attacks, the world has not ended.
I am also concerned about the anthropomorphization of AI in a lot of reporting, where LLMs and agents are unnecessarily treated as if they were people. If I wield a hammer, miss a nail, and accidentally dent the wall, it’s not the fault of the hammer. The problem lies in how I used the hammer. Similarly, if I prompt an agent and it hacks into someone else’s system, the responsibility lies with me, not the agent.
Of course, we want to build systems that are as safe and predictable as possible. (For example, an unsafe hammer would be one whose head randomly flies off under normal use.) Today’s agentic systems are not predictable, but I see no reason why, by applying sound engineering practices, we won’t be able to make them extremely safe to use. One new element in the forecasts of AI-enabled doom is AI companies disclaiming responsibility for their own products. “I didn’t do it; my out-of-control agent did!” There’s a balance to be struck between the responsibility of the tool maker and the tool user, but when something goes wrong, let’s hold the people building and/or using the hammer responsible, rather than the hammer. (By the way, if you’re worried about AI bioweapon risk, David Bellamy has a great post on why this, too, is overhyped. Briefly, the bottleneck in building a bioweapon is not intelligence, but lab work and manufacturing.)
Pausing AI progress will create much more harm than benefit. First, our adversaries will certainly not slow down. Second, engineering requires discovering problems empirically so we can fix them. If we pause AI by a decade, we will also delay finding and implementing safety engineering fixes by about the same duration.
Of course, the incentive to stoke fears — for regulatory capture, to garner attention, or to make one’s technology seem more powerful — remains the same as before. Disclaiming responsibility is a new one. Taking a hard technical look at the actual risks however, I see little factual basis for the degree of fear that’s been stoked up. We still have hard research and engineering work ahead to improve AI safety, but the beneficial applications continue to vastly outweigh the risks, and we should keep building.
[Original text (with links): deeplearning.ai/the-batch/is… ]
65
GPT-5.6 Sol in Codex nails it because it stays with the whole job, not just the code.
I can start with an outcome, and it investigates the context, plans, makes a focused change, runs the checks, follows CI and review feedback, then leaves a clean handoff.
1
1
80
That continuity is the difference for me. I stay in control of the decisions without having to manually drive every step or rebuild context. It feels less like asking AI to write code and more like running the whole engineering loop in one persistent workspace.
@thsottiaux @sama
43
Just ordered mine, can't wait for this! @thsottiaux @sama gotta be worth a complimentary reset right?! 😉❣️
Meet kbd-1.0-codex-micro, built with @work_louder.
Map the buttons and joystick to your workflow, and keep your pinned chats in view.
Get yours before stock returns 410.
114
In engineering and technology, success isn't solely determined by technical prowess or the ability to lead a team of peers. Equally important is managing up—developing a productive and positive relationship with your managers ...
daveodea.com/p/managing-up-h…
56
Elevating Web Application Performance Through Advanced Monitoring Techniques
blog.chekit.io/blog/Elevatin…
60
Dave ODea retweeted
20 mins until KO and the place is absolutely humming. Already had a rendition of The Fields of Athenry.
I’m hiring! If you are a software engineer and interested in joining our European R&D team here at SharpenCX please check out the page below for details. Happy to chat about this role, just reach out!
linkedin.com/posts/davedodea… – at Galway, Ireland
1
3
104
Dave ODea retweeted
BREAKING: @SharpenCX Acquires @OctopusCX (aka WebText) < with UCaaS and #CCaaS companies chasing elusive “enterprise” market, refreshing to see 1 focused on helping mid-market firms accomplish a digital transformation with an agent first-focus #CX buff.ly/44KZLyh – at Vila Nova de Gaia, Portugal
Delighted to be able to share this news! Looking forward to working alongside all of our new colleagues at @sharpentech 😁🎉 – at Galway, Ireland
We’re thrilled to announce we've acquired Webtext! This acquisition expands our mission to empower exceptional agent & customer experiences to on-premises contact centers, allowing rapid digital transformation. Read the Release: https://teapawt.net/t.co/DHevMzKIN9
2
133
Dave ODea retweeted
📷Training Gallery
Check out the latest images from the IRFU High Performance Centre.
#TikTokW6N #NothingLikeIt
Dave ODea retweeted
The Ireland Match Day Squad for Saturday's opening #TikTokW6N game against Wales in Cardiff! 🟢
#NothingLikeIt | #IrishRugby
Dave ODea retweeted
🏆 GRAND SLAM CHAMPIONS 🏆
World #1 @IrishRugby do it in Dublin! ☘️
We are watching one of the all-time greatest teams.
#GuinnessSixNations | #IREvENG










