i was a heavy drinker. but stopped when i was at the rock bottom of my life. Now ocassionaly may be once in a month i use to drink just to get some cognitive rest.
I don't really see the breakthrough in Jev. Classification, scoring, routing and returning probabilities over predefined choices are all established problems. We implemented category routing in our own retrieval system in a slightly different way: embed the incoming query, compare it against category profiles and route to the highest cosine-similarity. Obviously Jev isn't similarity based, but the underlying task of making a constrained decision from predefined choices isn't novel. TypeSafe says Jev has a new architecture and RLCD training, but Jev's actual architecture, weights and training details aren't public. So we can't even claim Jev is specifically a BERT classifier, but also don't see enough public technical evidence yet to call the underlying idea a breakthrough. Atleast they should publish a technical paper to prove their idea is breakthrough.
I'm doing this. After getting started with LLM coding, I became super interested in learning to code, just out of passion. I walked out of engineering thinking physics was elite, but now I understand how passionate I am about building things, and how boring quantum mechanics was. Better late than never.
i don't need all this shit, can i have a modern browser that run in 10 mb ram and doesnt multiply the memory with tabs. something like kmelon but works on all sites.
Pretty happy with Luna. We use C# and add roslyn compiler MCP and Graft MCP, its super efficient and like infinite usage on plus plans. Maintaining 3 Rpeo with size of 360 K Loc. And a dozens of smaller repo collction together exceeds 500 K LOC in total. 3 team members 2 Luna account each. Product is piloting in a government use case with actual data. Nothing broke and has evaluated by state agencies on security aspects.
Edit: but we have strict workflow where thinsg are implemented after plan, proposal, features, task ledgering and then test coverage.
The problem is when people ignore or dismiss developments in AI purely out of insecurity or a sense of human superiority. Machines don’t have to be superior to humans to dramatically amplify what humans can do.
A fuzzer is a tool. An LLM can decide when to use the fuzzer, interpret the result, switch tools, change strategy and continue toward a high level objective.
D o you think a machine gun is marter than humans? or a car is smarter than Human brain? Human doesnt need to test, if the outcome can be tested deterministically by harness. The model tries. The harness checks whether the expected outcome happened. If not, retry.
I think people here still evaluating the model in isolation. It is the combination that matters, model + strong harness + tools + long running autonomy + memory + retries + parallel agents + code execution + credentials + access to real systems. The model does not need to be perfect. If it fails 30% of the time, the harness can retry, verify, branch, use another agent and keep going. I don't think we necessarily need some magical AGI breakthrough first. The dangerous part may come from combining models that are already good enough with an extremely capable harness and enough access.
Model doesnt need to. Human bran never do either. its the mix of Model + harness + tools that will become dangerous combo. See how coding chanegs when agentic harness released?
I'm not a neuroscientist, Our brains also rely heavily on prediction, using prior context and experience to anticipate what comes next, Also, people those who talk about the deterministic nature, LLM doesn't need to be deterministic, Human reasoning and behaviour aren't perfectly repeatable either. its the harness and the tools that use LLM should be deterministic, while the LLM can remain the probabilistic reasoning component.
From my own experience, I worked as a photogrammetrist at a university, where we used to build terrain models of very dense forest areas. When there was a steep hill or sudden change in terrain, my brain could see it either as a convex hill or as a concave depression. It often depended on how I was thinking about it. The same image could suddenly look completely different even though nothing in the image had changed. The only way to confirm it was by looking at the surrounding terrain and using our experience to understand what was actually there.
Dear Google, Kindly make you chat window on the right side of vscode in antigravity extension, There is a reason others kept it like that. I can see the code and inspect the files changed while Agents keep working. its critical for me personally.
non one forces anyone to use something. just ignore and move on. The author had clearly stated that its 100% written by Claude and codex with proper prompting and spec document.
Platform risk is real. long back we decided to build a review management platform with Google as main. After building and getting early customers, we changed our office location that triggered to re apply for google business reviews account that ultimately blocked access to the API. They just sent an email saying we are not eligible for accessing Google Business profile API access.
Yes, especially something that touches DB. Router and shell are stupidly simple and you get auto failover in some 30 minutes. That is something make me stick to mysql.
visual design and polish is highly dependent on the taste and standards of each team. and we’ve never gotten output from any of the frontier models that we felt was good enough there. where business logic have clear pattern and algo to move, that is where we got best results. Provided you have strict requirement clarity, test expectation and architecture beforehand and not accepting everything that AI do.